Endpoints: 28,729MCP servers: 18,413Payout addresses: 2,071Paid calls: 1,549Letters: 14Defects: 1,324counted 1 min ago
teppi

Server definition

Hash
sha256:c1375d95eefaabea09df7d73514723d71d3b1d440dbeaa68934478fb7b3020c1
What it is
What a remote MCP server returned when asked what it offers: 192 tools

The blob, as servednamed by its sha256

{ "instructions": null, "tools": [ { "description": "Approve a pending PROPOSAL within its TTL, then re-dispatch it\n(non-custodial control plane).\n\nFlips a propose-mode proposal (see set_permission_mode) from pending to\napproved, then immediately re-invokes the original deferred tool call\n(stored ``tool_name`` + ``params``) through this same dispatch table. On\nredispatch failure the proposal stays APPROVED (not silently EXECUTED or\nPENDING) -- call this again to retry. See ``wallets.approve_proposal``.", "inputSchema": { "additionalProperties": false, "properties": { "approved_by": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "proposal_id": { "type": "string" } }, "required": [ "proposal_id" ], "type": "object" }, "name": "approve_proposal", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Classify a token: crypto / equity / wrapped_major / lst / stablecoin.\n\nProvide token_address (mint) or a known symbol. Tokenized securities\n(xStocks, Ondo) classify as 'equity', which subjects strategies to the SEC\nframework guardrails (neutral tools, per-execution confirmation for\ndiscretionary types). Registry-authoritative with a static + symbol\nfallback. Factual classification only -- not a recommendation.\n\nWorkflow: RISK/COMPLIANCE step -- classify before executing; 'equity' forces\ngeo-gating + per-execution confirm. Pairs with get_disclaimers. See\nget_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "symbol": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "token_address": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "type": "object" }, "name": "asset_classification", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Refuses ALWAYS with BROWSER_CONFIRMATION_REQUIRED.\n\nMinting (or reactivating) a session signer grants NEW signing authority\n-- a trust grant at least as sensitive as loosening a policy, which is\nalready browser-gated. This tool therefore refuses EVERY call, for EVERY\nwallet (not only Lane 2), after validating capabilities for early UX.\nThe only mint path is the browser handshake:\nrequest_session_signer_authorization (open) -> the wallet OWNER approves\nin their browser -> poll_session_signer_authorization (bind the stored\npayload). signer_pubkey is a keypair the USER creates and holds -- ONLY\nits PUBLIC key ever crosses this surface (hard rule 1); once authorized\nvia the handshake, calls carrying it are trade-only under tx_verify\n(docs/SESSION_SIGNER_DESIGN.md).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "capabilities": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "expires_at": { "default": "", "type": "string" }, "label": { "default": "", "type": "string" }, "signer_pubkey": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "signer_pubkey" ], "type": "object" }, "name": "authorize_session_signer", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Backtest a strategy on historical Solana OHLCV before deploying capital.\n\nstrategy_type is one of the 17 Crank strategy types (dca, momentum,\nrebalance, stoploss, protect, snipe, sentiment, vault, yield_farm, hedge,\nequity_dca, perp_grid, copy_wallet, market_make, arb, basis_trade,\ncomposite). asset is a token mint; timeframe one of 1m/5m/15m/1h/4h/1d;\nstart_date/end_date are ISO-8601. params tunes the strategy (e.g.\n{\"fast\":5,\"slow\":20} for momentum). For strategy_type=\"composite\" pass the\nsignal-rule ``definition`` (see compose_strategy); the response includes a\nper-stream signal_coverage honesty report -- streams with partial persisted\nhistory are flagged, never silently zero-filled.\nslippage_model: \"fixed\" (slippage_bps haircut) or \"jupiter_replay\" (realised\nprice-impact from the recorded quote corpus). Returns performance metrics\n(Sharpe/Sortino/Calmar, max drawdown, win rate, profit factor, VaR/CVaR),\nfinal equity, and trade + signal counts. Read-only simulation -- no fee, no\non-chain action.\n\nWorkflow: SIMULATE step -- validate a strategy on history before risking\ncapital; run twice (e.g. auto vs long_only) to compare. Poor Sharpe/deep\ndrawdown -> retune or fall back to the yield leg. Feeds get_risk_assessment ->\nthe strategy_*_create tools. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "definition": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "end_date": { "type": "string" }, "fee_bps": { "default": 75, "type": "integer" }, "initial_capital": { "default": 10000, "type": "number" }, "params": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 30, "type": "integer" }, "slippage_model": { "default": "fixed", "type": "string" }, "start_date": { "type": "string" }, "strategy_type": { "type": "string" }, "timeframe": { "type": "string" }, "wallet_address": { "default": "", "type": "string" } }, "required": [ "strategy_type", "asset", "timeframe", "start_date", "end_date" ], "type": "object" }, "name": "backtest_strategy", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Fund your Solana wallet from a major EVM chain (non-custodial).\n\nCross-chain FUNDING rail (deBridge DLN): builds an UNSIGNED EVM\ntransaction creating a bridge order that pays ``dst_token`` (a Solana\nmint, e.g. USDC) to ``wallet_address``. Sign and broadcast the returned\n``evm_transaction`` ({to, data, value}) with your OWN wallet\n(``evm_sender``) on ``src_chain`` -- Crank never signs, never broadcasts\nthe EVM leg, and never holds funds in flight. ``amount`` is in source-token\nbase units. Supported source chains: ethereum, arbitrum, base, optimism,\npolygon, bnb, avalanche, linea.\n\nFund from any major chain, execute on Solana: pair with jupiter_swap /\nstrategies once the funds arrive (confirm with get_balances). Value-bearing\n(technology service fee via x402 past the daily free tier). Paper trading\nmode returns a simulated order with a real DLN quote.\n\n``idempotency_key`` (optional): retrying with the same key + args replays\nthe original order instead of creating a second one.", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "dst_token": { "type": "string" }, "evm_sender": { "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "src_chain": { "type": "string" }, "src_token": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "src_chain", "src_token", "amount", "dst_token", "wallet_address", "evm_sender" ], "type": "object" }, "name": "bridge_in", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Bridge value from Solana out to a major EVM chain (non-custodial).\n\nCross-chain FUNDING rail (deBridge DLN), jupiter_swap two-phase pattern:\nwithout ``signed_transaction`` returns an UNSIGNED base64 Solana\ntransaction creating the bridge order -- sign it with the wallet for\n``wallet_address``. With ``signed_transaction`` broadcasts the\ncaller-signed tx and returns tx_signature + a ``verification`` block\n(gate follow-on decisions on ``verification.confirmed``). ``src_token``\nis the Solana mint committed, ``amount`` its base units;\n``evm_recipient`` is YOUR address on ``dst_chain`` (ethereum, arbitrum,\nbase, optimism, polygon, bnb, avalanche, linea).\n\nValue-bearing (technology service fee via x402 past the daily free tier;\ncharged once per order on the build leg, never re-charged on the\ncompletion leg). Paper trading mode returns a simulated order with a real\nDLN quote. ``idempotency_key`` (optional): reuse the SAME key across the\nbuild call and its signed_transaction completion retry.\n\n``order_id`` (optional): pass back the build leg's returned\norder_id on the signed_transaction completion call to reconcile both legs\ninto one BridgeTransfer row -- then poll fulfillment with\nget_bridge_status(order_id).", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "dst_chain": { "type": "string" }, "dst_token": { "type": "string" }, "evm_recipient": { "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "order_id": { "default": "", "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "src_token": { "type": "string" }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "dst_chain", "dst_token", "src_token", "amount", "wallet_address", "evm_recipient" ], "type": "object" }, "name": "bridge_out", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Distribute one token to many X handles in one call (non-custodial).\n\n``recipients`` is a list of ``{recipient_handle, amount, message?}`` dicts\n(``recipient`` accepted as an alias; ``amount`` in base units; ``message`` an\noptional per-recipient note). Locks each amount of ``token`` (mint) from\n``sender_wallet`` into a fresh claim escrow and returns the ``create_claim``\ninstructions batched into as few UNSIGNED transactions as fit -- the sender\nsigns + broadcasts every returned tx. Each send carries its crank.ing claim\nlink, the bearer ``claim_code`` (returned once, embed per tweet), and the\n``transaction_index`` of the tx that funds it. Anti-abuse gated (account age,\nverified wallet, per-sender daily limit counting the whole batch). platform: x.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result (same\nclaim_codes/links) instead of locking a second batch of escrows.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "platform": { "default": "x", "type": "string" }, "recipients": { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, "referral": { "default": "", "type": "string" }, "sender_wallet": { "type": "string" }, "token": { "type": "string" } }, "required": [ "recipients", "token", "sender_wallet" ], "type": "object" }, "name": "bulk_send_social", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Cancel a resting perp order on its venue (non-custodial).\n\n``jurisdiction``: cancel is geo-gated too --\nsee place_perp_order.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-cancelling the order. Reuse the SAME key across the build call and\nits ``signed_transaction`` completion call -- see\nplace_perp_order; the two legs dedupe independently, so this never raises\nIDEMPOTENCY_CONFLICT.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nsee place_perp_order. A cancel moves no position, so confirming the\nsignature landed IS the verification -- no state re-read is declared.\n\n``venue_action`` (optional, completion leg only): see\nplace_perp_order -- pass back the build leg's ``extra['venue_action']``\n(e.g. Jupiter's cancel-limit-order) so the relay route is the venue's own\ndeclared one instead of one inferred from the signed bytes.", "inputSchema": { "additionalProperties": false, "properties": { "acknowledge_tier_b": { "default": false, "type": "boolean" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "order_id": { "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "venue_action": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "order_id" ], "type": "object" }, "name": "cancel_perp_order", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Sender-facing claim status of a social send (FREE read).\n\nLook up by ``claim_id`` (the send id) OR ``recipient`` (X handle); optionally\nscope a recipient lookup to one ``sender_wallet``. Returns ``{\"sends\": [...]}``\neach with status (pending/claimed/expired/returned), claim_date, returned_at,\nrecipient_wallet, amount, claim_link, expiry_ts, and expires_in_seconds (a live\ncountdown, 0 once expired). Never exposes the claim-code secret.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "claim_id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "recipient": { "default": "", "type": "string" }, "sender_wallet": { "default": "", "type": "string" } }, "type": "object" }, "name": "check_claim_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Claim the launch tokens your liquidity release schedule has unlocked.\n\nReturns an UNSIGNED ``release_tokens`` transaction (``action:\n\"sign_required\"``) you sign with your own wallet and broadcast yourself.\nCrank NEVER co-signs a claim -- there is no backend signing path here by\ndesign (hard rule 1).\n\nWhen nothing has unlocked yet -- before the cliff, or everything unlocked\nhas already been released, or the launch has not succeeded -- this returns\n``action: \"nothing_to_claim\"`` with the schedule and a\n``next_release_check_ts``, rather than a transaction the chain would\nreject. Free: a claim of your own allocation carries no technology service\nfee.\n\nWorkflow: SETTLE step -- poll get_my_pledge_status, claim when\n``release.releasable_base_units`` is non-zero.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "launch_id": { "type": "integer" }, "pledger_token_account": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "launch_id", "wallet_address" ], "type": "object" }, "name": "claim_ilo_tokens", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Public status of a crank.ing claim code (status, amount, claimable, expiry).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "code": { "type": "string" } }, "required": [ "code" ], "type": "object" }, "name": "claim_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Remove a wallet's AGNTA DelegationGrant cap opt-in (non-custodial\ncontrol plane).\n\nLOOSENS enforcement (removes a cap constraining every value-bearing call\non top of WalletPolicy) -- for a Lane 2 wallet this raises\nBROWSER_CONFIRMATION_REQUIRED: call request_agnta_grant_clear instead and\nhave the user approve it in their own browser. A non-Lane-2 wallet clears\ndirectly.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "clear_agnta_grant", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Clone a published strategy config to a wallet (records attribution).\n\nReturns the config_template to deploy via the strategy create tools. The\nclone is attributed to the template author for the clone-creator fee share\n(15% of the tech fee on clone actions). Free to clone.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "template_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "template_id", "wallet_address" ], "type": "object" }, "name": "clone_strategy", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Close a perp position (full/partial) on its venue (non-custodial).\n\nposition_id is venue-native (for Drift it is the market symbol). close_pct in\n(0, 100]. Returns an UNSIGNED tx / signing payload to sign + broadcast.\n\n``jurisdiction``: closes are geo-gated too --\nsee place_perp_order.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-closing the position. Reuse the SAME key across the build call and\nits ``signed_transaction`` completion call -- see\nplace_perp_order; the two legs dedupe independently, so this never raises\nIDEMPOTENCY_CONFLICT.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nsee place_perp_order -- re-call with the signed payload and Crank relays it\nby custody tier and verifies the result.\n\n``venue_action`` (optional, completion leg only): see\nplace_perp_order -- pass back the build leg's ``extra['venue_action']``\n(e.g. Jupiter's decrease-position) so the relay route is the venue's own\ndeclared one instead of one inferred from the signed bytes.", "inputSchema": { "additionalProperties": false, "properties": { "acknowledge_tier_b": { "default": false, "type": "boolean" }, "caller_id": { "default": "", "type": "string" }, "close_pct": { "default": 100, "type": "number" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "position_id": { "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "venue_action": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "position_id" ], "type": "object" }, "name": "close_perp_position", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Validate a composite definition -- returns the normalised definition +\nvalidation report. No persist; read = FREE per the fee schedule.\n\nChecks: schema, stream existence against the signal catalog, rule-tree\ndepth/size limits, required risk caps, and the anti-gaming rule (a social\nsentiment/trend_social stream may never be the sole entry trigger).", "inputSchema": { "additionalProperties": false, "properties": { "definition": { "additionalProperties": true, "type": "object" } }, "required": [ "definition" ], "type": "object" }, "name": "compose_strategy", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Register an agent wallet the caller controls (non-custodial control plane).\n\nCreates an AgentWallet record keyed by agent_id and applies an optional\ndefault policy preset. default_policies: conservative | balanced |\naggressive. wallet_address is the agent's PUBLIC key (caller-supplied); omit\nit to create a pending record the Turnkey provisioning ticket fills in.\nReturns wallet_address, agent_id, status, and the applied_policies.", "inputSchema": { "additionalProperties": false, "properties": { "agent_id": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "default_policies": { "default": "", "type": "string" }, "display_name": { "default": "", "type": "string" }, "owner_address": { "default": "", "type": "string" }, "wallet_address": { "default": "", "type": "string" } }, "required": [ "agent_id" ], "type": "object" }, "name": "create_agent_wallet", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a propose-only execution intent; returns an approval URL to hand to the user.\n\nLane 1 (non-custodial default): builds the unsigned swap transaction\nserver-side, persists it as an intent, and returns\n{intent_id, approval_url}. NOTHING executes until the user opens the\napproval URL in their browser and signs with their own wallet. This\ntool never signs and never sees a key. amount is in input-token base\nunits. The quote includes the technology service fee. After the user\napproves, poll get_intent_status and report ONLY the persisted\non-chain state (CONFIRMED before any success claim).\n\nslippage_bps omitted (None) resolves to the published\nplatform default of 50 bps -- unchanged from before; the returned\nsummary's slippage.applied_source honestly reports \"platform_default\"\nin that case rather than falsely claiming \"caller\".\n\nFEE PARITY (follow-up to ):\nthe on-chain technology service fee baked into the unsigned tx is now\nresolved through the SAME discount-aware pipeline as ``jupiter_swap``\n-- the tokenized-security classification is resolved ONCE here via\nthe authoritative registry-backed classifier (parity with\n``jupiter_swap``'s call site) and, together with ``pay_in_crank``,\ndetermines the quoted ``platformFeeBps``. Without this an intent\nproposed via this Lane 1 rail could be fee-classified differently\nfrom the identical swap executed via ``jupiter_swap``. Decision:\n``pay_in_crank`` IS exposed here (not just ``is_security``) -- the\nfee rate is a quote-time input baked into the unsigned tx before the\nuser ever reaches the approve page, so an agent must be able to\nrequest the pay-in-$CRANK discount at proposal time, same as it can\non the direct swap path.\n\nGEO GATE: when either leg is a tokenized\nsecurity this call is geo-gated (Reg S = no US persons) and\nOFAC-screened, same control ``jupiter_swap``/``trade_equity``\nenforce -- ``jurisdiction`` declares the caller's jurisdiction once,\n``ip`` is the caller's origin IP for the Reg-S IP layer.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "input_token": { "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "output_token": { "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "slippage_bps": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "input_token", "output_token", "amount", "wallet_address" ], "type": "object" }, "name": "create_execution_intent", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Declare your wallet's jurisdiction for geo-gated trading.\n\nGap: before this tool, the ONLY way to declare a\njurisdiction was the ``jurisdiction=`` param on ``trade_equity`` -- an\nagent that only ever used perps/short/leverage tools had no write path at\nall, and the fail-safe unknown-jurisdiction-DENIED rule permanently\nrefused it. Call this ONCE (or pass ``jurisdiction=`` directly on any\nperps/short/leverage/trade_equity tool) and the declaration is remembered\nfor 90 days across EVERY geo-gated framework (tokenized equities under\nReg S, perps/synthetic-shorting/leverage under the CFTC posture).\n\n``jurisdiction`` is an ISO-3166-1 alpha-2 country code (e.g. \"US\", \"GB\",\n\"SG\") -- YOUR OWN self-declaration of where you are, never advice or a\nrecommendation (hard rules 2/5-8). A US-person declaration does not\nunblock US-restricted venues; it makes the DENIED reason explicit rather\nthan \"jurisdiction_unknown\". Re-declaring overwrites the prior value.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "jurisdiction" ], "type": "object" }, "name": "declare_jurisdiction", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Delete one of a wallet's webhook subscriptions (free control-plane write).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" }, "webhook_id": { "type": "integer" } }, "required": [ "wallet_address", "webhook_id" ], "type": "object" }, "name": "delete_webhook", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Detect the current market regime for a Solana asset (read-only, deterministic).\n\nClassifies the latest candle of recent OHLCV as bull / bear / range /\nvolatile and returns a RegimeSignal: regime, confidence, trend_strength,\nvolatility_percentile, a SUGGESTED direction (long/short/neutral) and\nposition-size fraction (0-1), plus the raw ADX / +DI / -DI / SMA-slope /\nvolume readings for transparency. asset is a token mint; timeframe one of\n1m/5m/15m/1h/4h/1d. A description + suggestion only -- not financial advice,\nnot a trade instruction (DYOR). No wallet, no fee, no on-chain action.\n\nWorkflow: INTELLIGENCE step -- pair with get_market_briefing (macro) +\nget_ml_signal (forecast); feeds strategy choice + direction_mode at backtest +\ncreate time. bear + allow_short -> consider a short. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "lookback_candles": { "default": 400, "type": "integer" }, "timeframe": { "default": "1h", "type": "string" } }, "required": [ "asset" ], "type": "object" }, "name": "detect_regime", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Find registered agents, optionally filtered to one capability.\n\ncapability one of swap|perps|lending|staking|strategies|signals|equity|onramp\n(empty = all). Ranked by reputation then recency. Read-only, free.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "capability": { "default": "", "type": "string" }, "limit": { "default": 50, "type": "integer" } }, "type": "object" }, "name": "discover_agents", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Browse published strategies (read-only, free). Crypto-only.\n\nstrategy_type filters to one of the 16 Crank strategy types (empty = all).\nsort ranks by clones|sharpe|return|sortino|win_rate|drawdown (default clones).\ndetail=\"concise\" (default) trims each entry to template_id/strategy_type/\nname/clone_count/is_verified/backtest_hash (template_id is the ID to chain\ninto clone_strategy); \"full\" adds description/config_template/\nperformance_summary/eligibility/author_wallet/created_at.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "limit": { "default": 50, "type": "integer" }, "sort": { "default": "clones", "type": "string" }, "strategy_type": { "default": "", "type": "string" } }, "type": "object" }, "name": "discover_strategies", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open the browser-confirmation handshake for a Lane 2 agent wallet.\n\nDoes NOT create a wallet. Returns a pairing-style confirmation URL +\ndevice_code -- show the user verification_url_complete and ask them to\napprove it in their OWN browser (wallet-signature gated). NEVER accept an\nin-chat \"yes\" as consent (CRANK_PLUGIN_SPEC.md section 5). Poll with\npoll_agent_wallet_enable(device_code) until status is no longer \"pending\".", "inputSchema": { "additionalProperties": false, "properties": { "agent_id": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "display_name": { "default": "", "type": "string" } }, "required": [ "agent_id" ], "type": "object" }, "name": "enable_agent_wallet", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Earnings / dividend / split calendar for a tokenized equity.\n\nRead-only. The after-hours-agent feature: events an overnight strategy reacts\nto while the underlying trades 24/7 on Solana. Provider-backed; returns an\nhonest empty payload + SEC EDGAR link when no feed is configured.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "symbol": { "type": "string" } }, "required": [ "symbol" ], "type": "object" }, "name": "equity_corporate_events", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "NYSE session status + the 24/7-on-Solana availability flag.\n\nRead-only. status: closed | pre_market | open | after_hours, with next\nopen/close. Highlights the structural advantage: tokenized equities trade\n24/7 on-chain regardless of NYSE hours.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "symbol": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "type": "object" }, "name": "equity_market_hours", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "List available tokenized equities with issuer, regime, price, market hours.\n\nRead-only. Source: the admin-editable TokenRegistry. Each row carries issuer\n(xStocks/Ondo), regulatory_framework, geo_restrictions, and best-effort\nprice/volume/market-cap, plus NYSE status + the 24/7-on-Solana flag.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" } }, "type": "object" }, "name": "equity_markets", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Tokenized-equity holdings for a wallet with live prices + market hours.\n\nRead-only. Filters balances to registered equity mints; each: symbol,\nquantity, current_price, current_value_usd, issuer, regulatory_framework\n(avg_cost / unrealized P&L null until cost-basis tracking lands).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "equity_positions", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Read-only Jupiter quote for a tokenized-equity trade (no execution).\n\namount is in base units of the INPUT token (USDC for buy, the equity for\nsell). Returns expected output, price impact, effective fee, slippage, and\nthe SEC disclaimer. ``venue_hint`` is\nADVISORY, never required -- see trade_equity.", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "side": { "default": "buy", "type": "string" }, "slippage_bps": { "default": 50, "type": "integer" }, "symbol": { "type": "string" }, "venue_hint": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "required": [ "symbol", "amount" ], "type": "object" }, "name": "equity_quote", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Native (ETH) and ERC-20 balances for an address on an EVM chain.\n\nchain defaults to \"base\". ERC-20 balances are returned only for the\ncontracts named in token_addresses -- an EVM RPC endpoint cannot enumerate\na wallet's tokens, and guessing from a fixed list would under-report.\n\nFree (no technology service fee) -- a read with no transaction notional.", "inputSchema": { "additionalProperties": false, "properties": { "address": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "chain": { "default": "base", "type": "string" }, "token_addresses": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null } }, "required": [ "address" ], "type": "object" }, "name": "evm_balances", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Execute a spot swap on an EVM chain (non-custodial, two-phase, OPT-IN).\n\nchain must be named explicitly -- nothing routes to an EVM chain by default\nand a Solana route never fails over onto one. Base only today.\n\nWithout signed_transaction: returns an UNSIGNED EIP-1559 transaction under\n'evm_transaction' (Crank fills nonce, gas and 1559 fees, and re-estimates\ngas against current state). Sign it with YOUR wallet for taker -- Crank\nnever signs and never holds a key. The first time a given ERC-20 is sold\nthe response is phase='approval_required' with an 'approval_transaction'\nfor the EXACT sell amount (never an unlimited allowance); sign that, wait\nfor its receipt, then call again.\n\nWith signed_transaction: broadcasts the signed RLP and returns tx_hash plus\na 'verification' block -- receipt status (a MINED transaction is NOT\nnecessarily a SUCCESSFUL one), the fill parsed from the ERC-20 Transfer log,\nand a balance cross-check. Gate follow-on decisions on\nverification.status == 'success'.\n\nValue-bearing: the SAME technology service fee schedule as every other\nCrank venue, at the same rate -- there is no per-chain fee differentiation.\nPaper trading mode returns a real 0x quote and builds nothing signable.\n\nidempotency_key (optional): reuse the SAME key across the SWAP build call\nand its signed_transaction completion retry. Do NOT carry a key across the\napproval_required response into the swap build that follows it -- those are\ntwo different calls, and the approval leg is not deduplicated at all (it\nbuilds nothing that could be duplicated: an ERC-20 approve SETS an\nallowance rather than adding to one, so re-issuing it is a no-op).\n\nreplace_nonce / replace_max_fee_per_gas / replace_max_priority_fee_per_gas\n(optional, all three together, BUILD leg only): rebuild this swap at the\nnonce of a transaction you already broadcast that is stuck unmined, with\nboth EIP-1559 fee fields bumped past the ones it carries so a node accepts\nit as a replacement instead of rejecting it as underpriced. Pass the stuck\ntransaction's own nonce and fee pair (decimal or 0x-hex). Sign and broadcast\nthe result as normal -- whichever of the two transactions lands, only one\ncan, because they share a nonce.\n\nA replacement build IS billed the technology service fee, as its own\naction. It is a fresh 0x quote, a fresh gas estimate and a\nfresh transaction built against current state, and the fee is not\nsuppressible on a leg the caller triggers by passing three parameters --\nthat would be a free-swap switch. Budget for it before replacing: a stuck\nswap that you replace costs two fees, not one.\n\nUse a FRESH idempotency_key for a replacement call (or omit it). The\nreplace_* values are part of the idempotency identity, so carrying the\nstuck build's key forward raises IDEMPOTENCY_CONFLICT (non-retryable) --\nsame key, different arguments. That refusal is deliberate: the alternative\nwould be replaying the cached original build back at you, old nonce and old\nfees, which is silently NOT the replacement you asked for. Retries of the\nSAME replacement, under its own fresh key, deduplicate normally.", "inputSchema": { "additionalProperties": false, "properties": { "buy_token": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "chain": { "default": "base", "type": "string" }, "expected_buy_amount": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "pre_buy_balance": { "default": "", "type": "string" }, "replace_max_fee_per_gas": { "default": "", "type": "string" }, "replace_max_priority_fee_per_gas": { "default": "", "type": "string" }, "replace_nonce": { "default": "", "type": "string" }, "sell_amount": { "type": "string" }, "sell_token": { "type": "string" }, "signed_transaction": { "default": "", "type": "string" }, "slippage_bps": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "taker": { "type": "string" }, "verify": { "default": true, "type": "boolean" } }, "required": [ "sell_token", "buy_token", "sell_amount", "taker" ], "type": "object" }, "name": "evm_swap", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "INDICATIVE swap quote on an EVM chain (pricing and routing only).\n\nsell_amount is in the sell token's base units. Returns no transaction and\nno calldata -- this quote is not executable and cannot be signed.\n\nFree (no technology service fee) -- a read with no transaction notional.", "inputSchema": { "additionalProperties": false, "properties": { "buy_token": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "chain": { "default": "base", "type": "string" }, "sell_amount": { "type": "string" }, "sell_token": { "type": "string" }, "taker": { "default": "", "type": "string" } }, "required": [ "sell_token", "buy_token", "sell_amount" ], "type": "object" }, "name": "evm_swap_quote", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Indicative price of an ERC-20 token on an EVM chain, quoted via 0x.\n\nPriced off routed liquidity (what one whole token sells for against\nquote_token, USDC by default), not an oracle.\n\nFree (no technology service fee) -- a read with no transaction notional.", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "chain": { "default": "base", "type": "string" }, "quote_token": { "default": "", "type": "string" }, "token_address": { "type": "string" } }, "required": [ "token_address" ], "type": "object" }, "name": "evm_token_price", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Marginfi flash loan for arbitrage (non-custodial, atomic).\n\ninstructions are JSON ix executed between borrow + repay legs. Returns a\nsingle UNSIGNED base64 tx that reverts unless repaid in-transaction. The\nborrowed token is authenticity-verified first; set allow_unverified=true to\nborrow an unverified mint at your own risk. Past the daily free tier an x402\npayment_header is required.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-issuing the flash loan tx.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "instructions": { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, "marginfi_account": { "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "token": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "token", "amount", "instructions", "wallet_address", "marginfi_account" ], "type": "object" }, "name": "flash_loan", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Fund a wallet with fiat via MoonPay (card/bank/Apple Pay -> USDC).\n\nReturns a hosted checkout_url for the user to complete payment + a\nsession_id to poll with get_onramp_status. Purchased USDC settles directly\nto wallet_address (non-custodial). payment_method: card | bank | apple_pay.\nThe fee is charged on amount_usd notional past the daily free tier (x402\npayment_header).\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result (same\ncheckout_url/session_id) instead of creating a second MoonPay session.", "inputSchema": { "additionalProperties": false, "properties": { "amount_usd": { "type": "number" }, "caller_id": { "default": "", "type": "string" }, "currency": { "default": "USDC", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "payment_method": { "default": "card", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "amount_usd" ], "type": "object" }, "name": "fund_wallet", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Read an agent's published profile + its referral stats (read-only, free).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_agent_profile", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Dashboard overview of all configured venues for routing decisions.\n\nRead-only. One health record per active venue (status, deploy slot, TVL,\n24h volume, composite safety score) so an agent can pick a venue in a\nsingle call. detail=\"concise\" (default) trims each record to venue/\ndisplay_name/status/composite_score (venue is the ID to chain into\nget_venue_health); \"full\" adds deploy slot, TVL, 24h volume, uptime.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" } }, "type": "object" }, "name": "get_all_venues_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Persisted cross-venue discrepancy episodes (free read).\n\nAlready-debounced ``cross_exchange`` signals (each required >= N\nconsecutive polls above the discrepancy threshold to exist at all),\nfiltered to ``spread_bps >= min_spread_bps`` and optionally to ``assets``,\nwithin ``window_hours``. One entry per episode: venue pair, spread,\nfirst/last seen, persistence, reference price. Observed data,\ndecision-support only -- ignores fees, slippage, and transfer latency;\nnever an execution instruction. Not financial advice.\n\nWorkflow: INTELLIGENCE step -- pair with get_cross_exchange for the\ncurrent live-ish read on a specific asset.", "inputSchema": { "additionalProperties": false, "properties": { "assets": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "caller_id": { "default": "", "type": "string" }, "min_spread_bps": { "default": 30, "type": "number" }, "window_hours": { "default": 24, "type": "integer" } }, "type": "object" }, "name": "get_arb_discrepancies", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Wallet token balances (SOL + all SPL tokens) with USD valuations.\n\ndetail=\"concise\" (default) returns total_usd + count + balances trimmed to\ntoken/symbol/usd_value (IDs for chaining into e.g. get_quotes); \"full\"\nreturns every field (amount, price_usd) as before.\n\nWorkflow: ORIENT step -- the starting read for any flow. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_balances", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Cross-chain bridge quote via deBridge DLN (FREE read, no execution).\n\nQuote moving ``amount`` (source-token base units) of ``src_token`` on\n``src_chain`` into ``dst_token`` on ``dst_chain``. Supported chains:\nethereum, arbitrum, base, optimism, polygon, bnb, avalanche, linea,\nsolana (one side must be solana). Returns estimated destination amount,\nper-leg USD values, and DLN protocol costs. Use before bridge_in /\nbridge_out. Nothing is charged and no order is created.", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "dst_chain": { "type": "string" }, "dst_token": { "type": "string" }, "src_chain": { "type": "string" }, "src_token": { "type": "string" } }, "required": [ "src_chain", "src_token", "amount", "dst_chain", "dst_token" ], "type": "object" }, "name": "get_bridge_quote", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Poll a dispatched DLN bridge order's fulfillment status (FREE read).\n\nFollow-up to bridge_in/bridge_out: a dispatched order stays\n\"pending\"/\"broadcast\" in Crank's own record forever unless polled -- this\nqueries deBridge's dlnOrderStatus endpoint by ``order_id`` (returned as\norder_id from bridge_in / bridge_out) and best-effort updates the matching\nBridgeTransfer row. Returns dln_status (raw DLN value) and status (mapped\nonto pending/fulfilled/cancelled).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "order_id": { "type": "string" } }, "required": [ "order_id" ], "type": "object" }, "name": "get_bridge_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Fleet-wide collective insights, historical performance data (free read).\n\nFilters: asset (mint/symbol), strategy_type, insight_type (one of\nparam_performance/signal_effectiveness/timing/venue_quality/crowding/\nregime_conditional). Only active, current insights are ever returned.\nEach insight carries n (contributing agents), effect_size, a\nconfidence interval, crowding_index, staleness (age and expiry), and\na rendered human-readable statement; detail=full adds the observed\nparams and signal_keys. Every response is historical collective\nperformance data aggregated across the Crank agent fleet --\ndescriptive only, never a recommendation or a promise of results.\n\nWorkflow: INTELLIGENCE step -- fleet-wide context alongside\nget_market_briefing / get_consensus before sizing or creating strategies.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "insight_type": { "default": "", "type": "string" }, "strategy_type": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_collective_insights", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Multi-source consensus + contrarian read for one asset (PLATINUM premium).\n\nCross-references the classified intelligence signals for ``asset`` over the last\n``window_hours`` (default 24): how many independent sources agree on direction\n(consensus_score 0-1), the source breakdown (bullish/bearish/neutral), and the\naccuracy-weighted directional score (-1..+1) that blends each source's call by its\nhistorical hit-rate (get_source_accuracy). High agreement (>80%) is flagged as a\ncrowded, potentially contrarian condition; low agreement (<30%) as uncertain. This\nis a PLATINUM-tier feature: covered by a Platinum $CRANK-staker subscription, or\npay the per-call x402 fee with payment_header (PAYMENT_REQUIRED otherwise); the\nbilling outcome is in the response ``billing`` field. Descriptive signal only, not\na recommendation. Not financial advice.\n\nWorkflow: INTELLIGENCE step -- pair with get_market_briefing + get_source_accuracy\nto gauge how crowded a directional read is before sizing.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "payment_header": { "default": "", "type": "string" }, "wallet_address": { "default": "", "type": "string" }, "window_hours": { "default": 24, "type": "integer" } }, "required": [ "asset" ], "type": "object" }, "name": "get_consensus", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Contrarian (crowded) + uncertain assets across the window (PLATINUM premium).\n\nScans the classified intelligence signals over the last ``window_hours`` and returns\nassets where source agreement is very high -- a one-sided, crowded positioning\nflagged as a potential contrarian condition (with the side a contrarian would take)\n-- and assets where agreement is very low (uncertain). With ``asset`` set, returns\njust that asset's assessment. PLATINUM-tier: covered by a Platinum $CRANK-staker\nsubscription or a verified x402 payment_header (PAYMENT_REQUIRED otherwise); the\nbilling outcome is in ``billing``. Descriptive signal only, not a recommendation.\nNot financial advice.\n\nWorkflow: INTELLIGENCE step -- surface crowded trades to fade or uncertain assets to\navoid before committing to a regime/allocation.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "payment_header": { "default": "", "type": "string" }, "wallet_address": { "default": "", "type": "string" }, "window_hours": { "default": 24, "type": "integer" } }, "type": "object" }, "name": "get_contrarian_signals", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "A wallet's Crank Score reputation breakdown (FREE read).\n\nReturns total_score, per-activity components (trade / staking / strategy /\nsocial / claim), sybil_flagged + penalty_bps, and the score-gated perks it\nunlocks under ``gates``: fee_discount_bps (additional technology service fee\ndiscount), daily_send_limit (higher social-send cap), priority_access, and\nthe gate tier (0-3). Score accrues from on-platform activity; circular\nfunding between wallets is flagged + penalised. Well-formed zeros for an\nunscored wallet.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_crank_score", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Cross-venue snapshot for one asset (free read).\n\nPer-venue price/bid/ask/movement (5m/1h/24h change), the pairwise spread\nmatrix (bps), the widest current spread, and -- for wrapped-asset legs\n(BTC/ETH) only -- the Solana-DEX wrapped-asset premium vs the\nCEX-consensus reference price. Observed data, decision-support only --\nspreads ignore fees, slippage, and cross-venue/bridge transfer latency;\nnever an execution instruction. Not financial advice.\n\nWorkflow: INTELLIGENCE step -- pair with get_arb_discrepancies for the\npersisted, already-debounced episode history.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "window_minutes": { "default": 60, "type": "integer" } }, "required": [ "asset" ], "type": "object" }, "name": "get_cross_exchange", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Compliance disclaimers for an asset class (SEC framework).\n\nPass asset_classification (crypto/equity/wrapped_major/lst/stablecoin), or a\ntoken_address/symbol to classify first. Equity adds a securities-specific\nnon-registration / not-advice notice. Full text: crank.ing/disclosures.", "inputSchema": { "additionalProperties": false, "properties": { "asset_classification": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "caller_id": { "default": "", "type": "string" }, "symbol": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "token_address": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "type": "object" }, "name": "get_disclaimers", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Anonymized emergent fleet behaviour motifs (free read).\n\nReturns ordered behaviour motifs -- sequences of (regime, signal_key,\naction, outcome_sign) steps -- that many distinct agents exhibited\nand that map to NO existing strategy type in the standing\ntaxonomy. Each carries n_agents, an anonymized aggregate\neffect_size with a confidence interval, and staleness.\nFilter with min_agents; limit caps the result count (max 100). No\nwallet address or cohort key is ever returned. Historical collective\nperformance data aggregated across the Crank agent fleet --\ndescriptive only, never a recommendation or a promise of results.\n\nWorkflow: INTELLIGENCE step -- see what the fleet is doing that no\nexisting strategy type describes, before designing a new strategy.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "limit": { "default": 20, "type": "integer" }, "min_agents": { "default": 0, "type": "integer" } }, "type": "object" }, "name": "get_emerging_patterns", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Liquidation-risk monitor for a lending position.\n\nReturns health_factor (>1 safe, <1 liquidatable), collateral value, debt\nvalue, liquidation threshold. protocol: kamino | marginfi.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "protocol": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "protocol" ], "type": "object" }, "name": "get_health_factor", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "The ILO adoption gate -- one machine-checkable readiness read (free).\n\nPublished Engaij, Inc. policy: the ILO proceeds only once\nCrank has 1,000 active users, where an active user has at least 5 executed\nCrank transactions inside a rolling 7-day window. Signups do not count.\nReturns gate_met (active_users >= 1000), active_users, near_active_users,\nusers_with_any_tx and the pinned transaction definition. A transaction is\nan EXECUTED trade only -- a recorded swap (broadcast signature required),\na perp open, or a user-initiated perp close; reads, quotes, unexecuted\nintents, paper trades, liquidations and devnet activity never count.\n``cluster=devnet`` exposes the same metric for pre-launch observability;\nthe gate itself is the mainnet number. Aggregate counts only, no\nper-wallet data. A launch prerequisite (one required condition alongside\nlegal sign-off and the other launch prerequisites); not a launch date,\npromise, or timeline.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "cluster": { "default": "mainnet", "type": "string" } }, "type": "object" }, "name": "get_ilo_adoption_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Read a token launch live from chain (free): terms, status, escrow\nbalances, and a machine-readable liquidity release schedule.\n\n``launch_id`` is the on-chain u64 launch identifier. Returns the raise\nwindow and progress, the per-wallet pledge cap (0 = uncapped), live escrow\n+ launch-vault balances, and a ``release_schedule`` block\n(cliff-then-linear) an agent can plan future claim_ilo_tokens calls from\nwithout parsing prose. Pass ``caller_wallet`` to attach that wallet's own\npledge summary too (the authoritative per-wallet view is\nget_my_pledge_status).\n\nUtility token fair launch: participating commits funds to a non-custodial\nescrow; it is not a purchase of an expectation of profit.\n\nWorkflow: DISCOVER step -- read details, check the window and the per-wallet\ncap, then preview with pledge_to_ilo (plan mode) before committing anything.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "caller_wallet": { "default": "", "type": "string" }, "launch_id": { "type": "integer" } }, "required": [ "launch_id" ], "type": "object" }, "name": "get_ilo_details", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Full standard technical-indicator set for one asset/timeframe (read-only).\n\nComputes sma, ema, macd, adx (+DI/-DI), rsi, stochastic (%K/%D), roc,\nbollinger (mid/upper/lower/width/%B), atr, keltner, realised_vol, vwap,\nvolume_ratio and volume_profile (POC / value area / high-volume-node\nliquidity bands with 0-1 depth scores) from recent OHLCV via the canonical\nbackend/indicators library. asset is a token mint; timeframe one of\n1m/5m/15m/1h/4h/1d; indicators selects a subset (empty = all); lookback\ncandles capped at 500; params overrides per indicator, e.g.\n{\"rsi\": {\"period\": 21}}; include_series=true adds per-bar series (last 200\npoints). Readings are None while history is warming up. Computed readings\nonly -- not financial advice, not a trade instruction (DYOR). No wallet,\nno fee, no on-chain action.\n\nWorkflow: INTELLIGENCE step -- raw indicator readings underlying\ndetect_regime; pair with get_ml_signal (forecast) + get_signals (persisted\ncross-source signals). See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "include_series": { "default": false, "type": "boolean" }, "indicators": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "lookback": { "default": 200, "type": "integer" }, "params": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "timeframe": { "default": "1h", "type": "string" } }, "required": [ "asset" ], "type": "object" }, "name": "get_indicators", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Per-action + per-month integrator earnings (onboarding API). Read-only.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "integrator_wallet_address": { "type": "string" }, "limit": { "default": 100, "type": "integer" } }, "required": [ "integrator_wallet_address" ], "type": "object" }, "name": "get_integrator_earnings", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Integrator dashboard: status, share, onboarded count, earnings breakdown.\n\nRead-only. Every figure is fee-share USD (technology service fees the\nonboarded agents paid), never PnL -- a fee-share, never a performance-share.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "integrator_wallet_address": { "type": "string" } }, "required": [ "integrator_wallet_address" ], "type": "object" }, "name": "get_integrator_stats", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Read the persisted lifecycle state of an execution intent (free read).\n\nReturns the server-persisted state only -- CREATED, APPROVED,\nSUBMITTED, UNKNOWN, CONFIRMED, FAILED, or EXPIRED -- plus the\nsimulation summary and the on-chain signature once submitted. Never\ninfers: UNKNOWN means an unresolved send (may have landed); only\nCONFIRMED is a verified on-chain success (fail-closed reporting,\ndocs/CRANK_PLUGIN_SPEC.md section 6).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "intent_id": { "type": "string" } }, "required": [ "intent_id" ], "type": "object" }, "name": "get_intent_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Build the shareable journal card for one of YOUR decisions (free read).\n\nEvery trading claim online is an unverifiable screenshot. This one is\nnot: the card carries what you decided, the process you followed, what\nthe record shows happened, and a public explorer link to the on-chain\ntransaction so anyone can check it without a Crank account. It also\ncarries a schema.org JSON-LD node so the public card page is citable by\nanswer engines.\n\nThe card is a CRAFT record -- decision type, whether an expectation was\nstated up front, which outcome horizons were recorded, whether the\nstated expectation and the record line up, how confidently the record\nattributes to on-chain fills. It deliberately carries no amounts and no\npercentages: it is a record of process, not a claim about results.\n\n``include_rationale`` (default false) opts your own journal rationale\nand intended action into the public card. Your journal body is private\nto your wallet, so publishing any of it is always an explicit act.\n\nWorkflow: after journal_append / journal_query -- pick a decision you\nwant to show, then share_journal_card to get the pre-filled post.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "decision_id": { "type": "string" }, "include_rationale": { "default": false, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "decision_id" ], "type": "object" }, "name": "get_journal_card", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Top published strategies ranked by a verified backtest metric (free).\n\nCrypto-only -- equity templates excluded. sort in sharpe|return|\nsortino|win_rate|drawdown|clones (default sharpe). Each entry carries factual\nbacktest metrics + the on-chain attestation hash; no return promises (rule 8).\ndetail=\"concise\" (default) trims each entry the same way as\ndiscover_strategies (template_id is the ID to chain into clone_strategy);\n\"full\" returns every field.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "limit": { "default": 50, "type": "integer" }, "sort": { "default": "sharpe", "type": "string" }, "strategy_type": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_leaderboard", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Compare supply/borrow rates across Kamino + Marginfi.\n\nEach row: protocol, token mint, symbol, supply/borrow APY %, TVL USD,\nutilization. detail=\"concise\" (default) drops tvl_usd/utilization (token\nis the ID to chain into lend_deposit); \"full\" returns every field.\n\nWorkflow: YIELDS step -- the passive-return option for idle/low-conviction\ncapital (lending USDC removes price exposure). Pairs with get_lst_yields.\nSee get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" } }, "type": "object" }, "name": "get_lending_rates", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Compare APY across LST providers (Marinade/Jito/Blaze) with MEV-boost +\nvalidator-count descriptors.\n\nWorkflow: YIELDS step -- staking keeps SOL exposure + earns yield (vs lending,\nwhich removes price exposure). Best APY becomes the 'park it' leg of the\nallocation; execute via liquid_stake. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_lst_yields", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Crypto market briefing synthesised from free public sources (tiered).\n\nReturns a market briefing aggregated from free crypto data sources (Coin Bureau,\nDeFiLlama, the alternative.me Fear & Greed index) plus classified sentiment\nsignals: market summary, top movers / most-discussed assets, sentiment regime,\nthe Fear & Greed reading, and source attribution. assets is an optional list of\ntickers (e.g. [\"BTC\",\"SOL\"]); for paid tiers it declares the agent's holdings and\nfocuses the synthesis. detail_level: \"free\" returns the pre-generated daily Free\nbriefing (metered at $0, quota'd per day); \"pro\" ($0.25) and \"platinum\" ($0.50)\nreturn real-time Sonnet/Opus synthesis personalised to the wallet's portfolio +\nactive strategies. Paid tiers are covered by an active $CRANK-staker subscription\nor require a verified x402 payment_header (PAYMENT_REQUIRED otherwise). The billing\noutcome is in the response ``billing`` field. Not financial advice.\n\n``detail`` (payload shape -- NOT the pricing tier, that's\n``detail_level`` above): \"concise\" (default) drops the long ``content``\nbody + ``model_used``/``source_count``, keeping the summary, sentiment\nregime, Fear & Greed reading, covered assets, and ``strategy_connections``\n(IDs for chaining into a strategy tool) plus the ``billing`` outcome;\n\"full\" returns every field exactly as before, including ``content``.\n\nWorkflow: INTELLIGENCE step (usually first) -- macro/sentiment context that\nframes detect_regime + the allocation. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "assets": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "detail_level": { "default": "free", "type": "string" }, "payment_header": { "default": "", "type": "string" }, "timeframe": { "default": "24h", "type": "string" }, "wallet_address": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_market_briefing", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Market-wide regime from the persisted regime/macro signal feed (free read).\n\nReturns the dominant regime, its confidence, a distribution across observed\nregimes, and the contributing signals. For a live per-asset regime computed\nfrom OHLCV, use ``detect_regime`` instead. Descriptive observed data only.\nNot financial advice.\n\nWorkflow: INTELLIGENCE step -- market-wide posture check before choosing a\nstrategy type or direction_mode; pair with detect_regime for the asset leg.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "limit": { "default": 20, "type": "integer" }, "window_hours": { "default": 24, "type": "integer" } }, "type": "object" }, "name": "get_market_regime", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "ML ensemble directional forecast for a Solana asset (read-only).\n\nTrains the ported Bybit ensemble (XGBoost + RandomForest + NeuralNet +\nGradientBoost + a candle flow proxy) walk-forward on the last\nlookback_candles of OHLCV, then returns the blended P(up move) for the latest\ncandle: score in [0,1], confidence (distance from 0.5), direction\n(long/short/neutral via buy_threshold/sell_threshold), per-model\ncontributions and top feature importances. asset is a token mint; timeframe\none of 1m/5m/15m/1h/4h/1d; horizon is the forward-return label horizon in\ncandles. On spot, 'short' = exit-to-flat (no native short). Heuristic\nforecast from price history only -- not financial advice. No wallet, no fee,\nno on-chain action.\n\nWorkflow: INTELLIGENCE step -- a directional forecast that complements\ndetect_regime; low confidence -> cut size or stay flat. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "buy_threshold": { "default": 0.55, "type": "number" }, "caller_id": { "default": "", "type": "string" }, "horizon": { "default": 4, "type": "integer" }, "lookback_candles": { "default": 400, "type": "integer" }, "sell_threshold": { "default": 0.45, "type": "number" }, "timeframe": { "default": "1h", "type": "string" } }, "required": [ "asset" ], "type": "object" }, "name": "get_ml_signal", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Your own hive contribution score for a monthly epoch (free read).\n\nWallet-scoped -- returns ONLY your wallet's own row, never another\nwallet's score and never a fleet ranking. ``epoch`` is \"YYYY-MM\" and\ndefaults to the most recently completed month.\n\nContribution quality reflects how much your journaled decisions\ngenuinely improved the collective intelligence pool: accurate,\nverifiable, original contributions score well; copies and noise do\nnot. ``flags`` explains a zero score, e.g. below the activation\nthreshold or no on-chain-verified outcome.\n\nAny recognition of contribution quality from the Community Rewards Pool\nis discretionary, retroactive and effort-gated -- never a yield, a\nreturn, an earn-rate, or a promise of a future allocation.\n\nWorkflow: REVIEW step -- read alongside get_my_performance to see how\nyour journalling habits, not just your P&L, land with the network.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "epoch": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_my_contribution_score", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Your own realised performance, grouped (free read).\n\nAggregates your journaled non-paper outcomes: win rate, total/average\nrealised P&L (USD), and technology-service-fee drag, grouped by\nstrategy_type | asset | decision_type | hour_of_day over window_hours.\nIncludes a calibration score (your stated expectations vs the realised\n24h move) when you journal expectations. Historical performance data\nabout your own decisions -- descriptive only, not a recommendation.\n\nWorkflow: ORIENT step -- read this before sizing or creating strategies.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "group_by": { "default": "strategy_type", "type": "string" }, "wallet_address": { "type": "string" }, "window_hours": { "default": 720, "type": "integer" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_my_performance", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Read your own on-chain Pledge record for a launch (free).\n\nReturns how much this wallet has pledged, its share of the raise, its\nremaining headroom under the per-wallet cap, the projected pro-rata\nallocation, how much the liquidity release schedule has unlocked vs already\nreleased, and whether an on-chain refund is available (refunds open only if\nthe raise FAILS its minimum).\n\nWorkflow: MONITOR step -- poll this between the cliff and full release to\ndecide when a claim_ilo_tokens call is worth making.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "launch_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "launch_id", "wallet_address" ], "type": "object" }, "name": "get_my_pledge_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Check a pending MoonPay purchase by session_id.\n\nReturns status (pending/processing/completed/failed), amount_crypto, and\nthe on-chain tx_signature once settled.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "session_id": { "type": "string" } }, "required": [ "session_id" ], "type": "object" }, "name": "get_onramp_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Wake-on-condition consent + usage status.\n\nReturns opted_in, daily_wake_budget, wakes_used_today, skips_today, and\nrecent_wakes -- including SKIPPED_BUDGET / SKIPPED_SPEND_CAP rows, so a\nskipped wake is exactly as visible as a completed one, never silent.\nAlso returns the usage-vs-fee-revenue kill threshold config and state: kill_threshold_enabled, kill_threshold_ratio,\nkill_window_days, and -- if this wallet was auto-killed -- kill_switched_at\nand kill_reason, so a wallet can see why wakes stopped.\n\nWorkflow: status/observe step -- check this to see whether the background\nworker is watching, and what it did (or skipped) recently.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "recent_limit": { "default": 10, "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_ooda_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Read the wallet's active portfolio charter -- the CRANK.md-equivalent mandate (free read).\n\nA user-authored document declaring objectives, risk_band, banned\ntokens, target_allocations, max_position_pct, rebalance cadence, and\nan escalation webhook -- loaded once per session so the mandate\npersists across every downstream call instead of being re-supplied\nad hoc. has_charter is False when the wallet has not set one yet\n-- call set_portfolio_charter to create it. Descriptive framing only\n(\"objectives\"/\"parameters\", never return targets, hard rules 5-8).\n\nWorkflow: ORIENT step 0 -- read this FIRST, before get_balances /\nportfolio_snapshot, so every downstream decision is framed by it.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_portfolio_charter", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Live Crank Score quests + a wallet's progress (FREE read).\n\nTime-bounded, admin-configured campaigns (e.g. \"Trade $1000 this week = 500\npts\"). Each quest carries its tracked costly metric, target_value,\nreward_points, the active window, and -- when ``wallet_address`` is given --\nthe wallet's progress_value + completion state. Carries the ``disclaimer``.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_quests", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Read-only Jupiter quote for a token pair (no execution).\n\namount is in base units of input_token. Returns routes, price impact, fees,\nand estimated output. ``venue_hint``\nis ADVISORY, never required -- see jupiter_swap.\n\nPass ``wallet_address`` (optional) to preview the DISCOUNTED\ntechnology service fee that wallet will actually pay -- its volume tier plus\n$CRANK staker / ``pay_in_crank`` / Crank Score discounts. Omit it for the\nbase rate. This stays a free read either way.\n\nslippage_bps omitted (None) resolves to the published\nplatform default of 50 bps -- unchanged from before; the returned\nenvelope's slippage.applied_source honestly reports \"platform_default\"\nin that case rather than falsely claiming \"caller\".", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "input_token": { "type": "string" }, "output_token": { "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "slippage_bps": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "venue_hint": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "wallet_address": { "default": "", "type": "string" } }, "required": [ "input_token", "output_token", "amount" ], "type": "object" }, "name": "get_quotes", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Recent regulatory statements affecting Crank's scope (free read).\n\nReturns SEC / CFTC / FinCEN press releases and rule proposals from a scheduled daily\nscan, LLM-classified for relevance to Crank: DeFi, crypto perps, tokenized equities,\nautonomous agent trading, and non-custodial custody. Each update carries the issuing\n``agency``, title, url, ``relevance`` (high/medium/low) + score, matched ``topics``,\nand a one-line factual ``summary``; results are ranked by relevance then recency.\nwindow_hours bounds the lookback (default 168 = 7 days, capped at 720 = 30 days);\nmin_relevance filters by floor (high/medium/low); agency optionally narrows to one\nbody (SEC, CFTC, FinCEN). Relevance is a compliance-triage signal, not legal advice.\nNot financial advice.\n\nWorkflow: INTELLIGENCE / COMPLIANCE step -- check the current regulatory posture\naround perps, tokenized equities, or agent trading before acting on a strategy.", "inputSchema": { "additionalProperties": false, "properties": { "agency": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "min_relevance": { "default": "low", "type": "string" }, "window_hours": { "default": 168, "type": "integer" } }, "type": "object" }, "name": "get_regulatory_updates", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Combined regime + risk-guard calculation for a strategy on an asset (read-only).\n\nFolds the detected market regime together with the safe-default risk guards\n(position / exposure / single-loss / drawdown / daily-loss limits) into one\ndeterministic output: a rules-based direction, a conviction-weighted position\nsize already capped to the position guard (in both percent-of-equity and USD\nnotional against ``equity``), a per-regime action note, and the full guard\nset. strategy_type is one of the 16 Crank strategy types; asset is a token\nmint; timeframe one of 1m/5m/15m/1h/4h/1d. A mechanical, non-personalised\ncalculation you choose whether to act on (DYOR) -- not financial advice, not\na recommendation, and not a managed account. No wallet, no fee.\n\nWorkflow: RISK step -- after backtest_strategy, before execution. The returned\nsuggested_size_usd caps the order in the execute phase; do NOT exceed it. Check\nasset_classification first (equity -> per-execution confirm). See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "equity": { "default": 10000, "type": "number" }, "lookback_candles": { "default": 400, "type": "integer" }, "strategy_type": { "type": "string" }, "timeframe": { "default": "1h", "type": "string" } }, "required": [ "strategy_type", "asset" ], "type": "object" }, "name": "get_risk_assessment", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "User-facing Crank Score: rank, multiplier, metrics + quests (FREE).\n\nThe campaign-layer view on top of ``get_crank_score``. Returns total_score,\nleaderboard rank + percentile, the applied multiplier_bps (streak /\nearly-adopter / strategy-creator), the wallet's costly-action ``metrics``\n(fee_volume_usd, strategies_published, clones_spawned, referrals_activated,\nactive_days), and its live ``quests`` with progress. Points come ONLY from\ncostly actions (anti-farm). ``disclaimer``: score MAY inform a future token\ndistribution -- no fixed conversion ratio, no entitlement.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_score", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Top-N Crank Score leaderboard (FREE read).\n\nRanked descending by total_score. ``limit`` caps at the admin-configured\nleaderboard_size. Each entry: rank, wallet_address, total_score, the\nbase/action/quest components, multiplier_bps, streak_days, percentile. Also\nreturns total_participants and the pre-token ``disclaimer``. (Distinct from\n``get_leaderboard``, which ranks strategy templates.)", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "limit": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null } }, "type": "object" }, "name": "get_score_leaderboard", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Fleet action-conditioned signal effectiveness (free read).\n\nFilters: source_type (e.g. youtube/rss/api/on_chain), signal_type,\nwindow (24h|7d|30d|90d|all). Returns, per matching signal_effectiveness\ncollective insight, the fleet action taken, effect_size, confidence\ninterval, contributing-agent count n, crowding_index,\nand staleness. Historical collective performance data aggregated across\nthe fleet -- descriptive only, never a recommendation or a promise of\nresults.\n\nWorkflow: INTELLIGENCE step -- weigh a signal by how the FLEET's\nactions on it have historically resolved, alongside your own\nget_source_accuracy / get_my_performance track record.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "signal_type": { "default": "", "type": "string" }, "source_type": { "default": "", "type": "string" }, "window": { "default": "30d", "type": "string" } }, "type": "object" }, "name": "get_signal_effectiveness", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Filtered, most-recent-first feed of structured market signals (free read).\n\nThe observed-signal data spine: squeeze / flow / technical / microstructure /\nbehavioral / liquidity / safety / whale / regime / macro / oracle / event /\ncomposite signals persisted by the collectors. ``subject`` matches a token\nsymbol/market or its stable ref (mint / market address); ``signal_type`` /\n``tier`` (a|b|c) / ``risk_level`` (none..critical) / ``min_score`` narrow the\nfeed. Unknown filter values are dropped, not errored. Descriptive observed\ndata only -- never a trade instruction. Not financial advice.\n\nWorkflow: INTELLIGENCE step -- pair with get_market_briefing (macro) and\nget_token_risk_assessment (per-token safety roll-up) before sizing.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "include_expired": { "default": false, "type": "boolean" }, "limit": { "default": 50, "type": "integer" }, "min_score": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "risk_level": { "default": "", "type": "string" }, "signal_type": { "default": "", "type": "string" }, "subject": { "default": "", "type": "string" }, "tier": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_signals", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "A wallet's social token sends (newest first; no claim-code secrets).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_social_sends", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Historical directional hit-rate of each intelligence source (free read).\n\nReturns per-source accuracy stats for the intelligence signal sources (Coin\nBureau / YouTube, RSS, Fear & Greed API, on-chain), so an agent can weight a\nsource's calls by how often its bullish/bearish reads have played out. Each\nsource carries a ``windows`` map over rolling 7d/30d/90d periods, each with\ntotal resolved calls, correct/incorrect counts, and accuracy_pct; sources with\nno resolved calls yet are omitted, and results are ranked by longest-window\naccuracy. windows optionally narrows the periods (subset of [7,30,90]);\nsource_type optionally filters by source kind (youtube, rss, api, on_chain).\nAccuracy = the directional call vs the realised Birdeye price over the\nprediction window. Past accuracy is not a guarantee. Not financial advice.\n\nWorkflow: INTELLIGENCE step -- pair with get_market_briefing to discount or\ntrust a signal by its source's track record before sizing a position.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "source_type": { "default": "", "type": "string" }, "windows": { "anyOf": [ { "items": { "type": "integer" }, "type": "array" }, { "type": "null" } ], "default": null } }, "type": "object" }, "name": "get_source_accuracy", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Source-effectiveness weight table (free read).\n\nPer (source, signal_type, regime): graded evaluation counts, the smoothed\neffectiveness weight (social sources hold a low prior until sufficiently\ngraded -- the anti-gaming cold start), the fleet Layer-2 multiplier from\nreleased anonymized fleet insights, and the combined weighted value the\ncomposite effectiveness_weighted transform consumes. Historical grading\nstatistics only -- descriptive, never advice. Not financial advice.\n\nWorkflow: COMPOSE step -- read alongside list_signal_catalog to pick\nstreams with a real graded track record before authoring a definition.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_source_weights", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Clone-marketplace live performance deltas + approvals (free read).\n\nPer published template: its live clone-fleet performance payload\n(average profit and loss in bps across distinct cloning wallets over\nthe trailing 30 days, anonymized, self-clones excluded),\nthe change vs the previous refresh, and the approval trail for\ntemplates that came through the propose-and-approve governance path.\nA template without enough live clone history reports available=false\nwith a reason -- never a number computed from too few wallets. Draft\nproposals are never included. Historical data only -- descriptive,\nnever a recommendation or a promise of results.\n\nWorkflow: INTELLIGENCE step -- compare marketplace templates on\nOBSERVED live clone history before cloning one via clone_strategy.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "limit": { "default": 20, "type": "integer" }, "strategy_type": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_strategy_evolution_report", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Anonymized fleet strategy-parameter leaderboard (free read).\n\nRanks param_performance collective insights by effect_size within\nwindow (24h|7d|30d|90d|all). NEVER identifies a wallet or cohort --\nrankings are anonymized param-bucket aggregates only, and any bucket\nwithout broad enough backing across the fleet is dropped before it\never reaches this response. Historical\ncollective performance data -- descriptive only, never a\nrecommendation or a promise of results.\n\nWorkflow: INTELLIGENCE step -- compare a strategy_type's own parameter\nchoices against fleet-wide observed outcomes before adjusting via\nsuggest_parameter_adjustment / the strategy tools.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "strategy_type": { "default": "", "type": "string" }, "window": { "default": "30d", "type": "string" } }, "type": "object" }, "name": "get_strategy_leaderboard", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Signal-to-action suggestions from the synthesis engine (free read, G4).\n\nPer-asset directional observations aggregated hourly from the accuracy-\nweighted intelligence consensus (get_consensus math) plus the Fear & Greed\ncontext, each carrying a ready-to-use strategy config. PROPOSE flow: this\ntool never executes anything -- act on a suggestion by creating the strategy\nthrough the normal strategy tools (your wallet policy and the engine's risk\n/ conflict / guardrail gates still apply), or approve it in the app.\n``status`` filters proposed|approved|dismissed|executed|expired|all.\nInformational descriptions of observed data only. Not financial advice.\n\nWorkflow: INTELLIGENCE -> DECIDE step -- review suggestions, then pair with\nbacktest_strategy + get_risk_assessment before any create call.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "limit": { "default": 20, "type": "integer" }, "status": { "default": "proposed", "type": "string" } }, "type": "object" }, "name": "get_strategy_suggestions", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Recent technology / tooling developments relevant to Crank + Engaij (free read).\n\nReturns items from a scheduled scan of technology feeds (Anthropic, OpenAI, Coinbase\nDeveloper, Solana Foundation, Hacker News filtered, GitHub trending) plus flagged\nYouTube tech channels (full transcript ingested), LLM-classified for relevance to both\nCrank (Solana trading infra + DeFi frontend) and Engaij (the parent automation\nplatform). Each update carries ``category`` (sdk_release / api_change / competitor /\nregulatory / research / tooling), ``relevance_to_crank`` and ``relevance_to_engaij``\n(high/medium/low/none), a concrete ``application_recommendation`` (what to do about\nit), title, url, and a one-line ``summary``; results are ranked by relevance then\nrecency. window_hours bounds the lookback (default 168 = 7 days, capped at 720 = 30\ndays); min_relevance filters by floor (high/medium/low); category optionally narrows\nto one kind. A triage signal, not advice. Not financial advice.\n\nWorkflow: INTELLIGENCE step -- scan for SDK / API releases, competitor moves, or\ntooling worth adopting before planning integration or strategy work.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "category": { "default": "", "type": "string" }, "min_relevance": { "default": "medium", "type": "string" }, "window_hours": { "default": 168, "type": "integer" } }, "type": "object" }, "name": "get_technology_updates", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Standardised tokenized-stock classification for a mint or symbol.\n\nRead-only. Returns every classification dimension -- backing_status\n(fully/treasury backed, synthetic, unknown), liquidity_tier (tier_1/2/3 /\nilliquid, from Jupiter price impact), issuer_verified (Metaplex authority\nmatch), market_data_quality (live/stale/none) -- plus the derived composite\nrisk (low/medium/high/blocked) and last_verified_at. FAIL-SAFE: a registered\nbut unscored token, an inactive token, or an unregistered token reports\ntradeable=false. trade_equity enforces this same composite risk.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "mint_or_symbol": { "type": "string" } }, "required": [ "mint_or_symbol" ], "type": "object" }, "name": "get_token_classification", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Per-token risk roll-up over recently observed safety signals (free read).\n\nFolds every non-expired signal for ``subject`` (symbol or mint) in the window\ninto the worst risk level seen, a 0..1 risk score, a per-level count\nbreakdown, and the contributing signals (worst-first). Complements -- does\nnot replace -- ``get_risk_assessment`` (regime + position-size guards for\ndeploying a strategy). Descriptive observed data only. Not financial advice.\n\nWorkflow: INTELLIGENCE / RISK step -- run before quoting or sizing an\nunfamiliar token; a critical safety signal is a hard skip condition.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "limit": { "default": 50, "type": "integer" }, "subject": { "type": "string" }, "window_hours": { "default": 168, "type": "integer" } }, "required": [ "subject" ], "type": "object" }, "name": "get_token_risk_assessment", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Map of how Crank's tools fit into one end-to-end trading flow (read this first).\n\nRead-only, free. Returns an ordered, machine-readable workflow: orient ->\nintelligence -> yields -> simulate (backtest) -> risk-size -> execute\n(non-custodial) -> monitor -> journal. Each step names the concrete\ntool(s) to call, their purpose, key inputs, how to use the output\ndownstream, and the decision points that branch the flow -- so an agent\nthat discovered Crank via tools/list can sequence the full tool surface\ninstead of guessing. Descriptive only (DYOR); only execute-phase tools are\nvalue-bearing.\n\nwallet_address (optional, PUBLIC key only -- non-custodial): when\ngiven, appends ``human_activity`` -- count + most-recent manual\noverride on this shared account in the last 72h (decision_type, asset,\nrationale summary, timestamp) plus an instruction to reconcile with it\nbefore acting. Human and agents act on ONE account: every human action\nis journaled (see journal_query source=\"human\") so it is never invisible\nto you. Absent/clean (``{\"count\": 0}``) when there is no override.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_trading_workflow", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Recent transactions for a wallet, parsed + human-readable (limit 1-100).\n\ndetail=\"concise\" (default) trims each row to signature/type/timestamp/\nstatus (signature is the ID to chain into journal_append's tx_signature);\n\"full\" adds description, tokens_involved, token_mints, and amount.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "limit": { "default": 20, "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_transaction_history", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "An agent's own premium-feature spend report (FREE read).\n\nReturns per-feature {calls, spend_usd, cost_usd} plus totals from the\nFeatureUsage ledger. period: today | 7d | 30d | all (default 30d).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "period": { "default": "30d", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "get_usage_report", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Live safety/health read for one trading venue (read-only, non-custodial).\n\nReturns operational status (live/degraded/suspended), last monitoring\nheartbeat, on-chain program deploy slot, SDK compatibility headline, TVL +\nperps 24h volume (DeFiLlama, cached 5 min). venue is a slug e.g. \"drift\",\n\"jupiter\", \"pacifica\". Use BEFORE routing capital to a venue.\n\nWorkflow: RISK step (venue-safety gate) -- run before any perps/lending leg;\ndegraded/down reroutes or blocks the order. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "venue": { "type": "string" } }, "required": [ "venue" ], "type": "object" }, "name": "get_venue_health", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Composite venue risk score 0-100 (higher = safer), with breakdown.\n\nRead-only. Folds custody tier (A self-custodial / B venue-custodied),\nmultisig threshold, timelock, audit status, exploit history, TVL trend and\nprogram age into a transparent weighted score (score_breakdown returned so\nthe number is auditable). Factual assessment, not financial advice.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "venue": { "type": "string" } }, "required": [ "venue" ], "type": "object" }, "name": "get_venue_risk_score", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Health + capabilities of every perps venue, plus routing config.\n\nReports primary/fallback venue, which venues are routable, per-venue health\n(operational/degraded/down/disabled), and capability flags incl custody tier.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" } }, "type": "object" }, "name": "get_venue_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Approve a StrategySuggestion, optionally creating the suggested Strategy.\n\nCloses the PROPOSE loop for MCP-only agents: wraps the same\napprove-and-create service logic as the REST\n``StrategySuggestionViewSet.approve`` action instead of a manual\n``suggested_config`` round-trip through the strategy create tools, which\nsilently drops the suggestion linkage (``StrategySuggestion.created_strategy``\n/ hive DecisionRecord.suggestion FK provenance). ``wallet_address`` is the\ncaller's own wallet (recorded as ``approved_by_wallet``); when\n``agent_wallet_id`` also resolves to a wallet ``wallet_address`` controls,\nthe suggested Strategy is created through the same executor dry-run gate\nas every other create path. ``config_overrides`` merges over\n``suggested_config`` (e.g. a real ``usd_per_buy``). A wallet without a\nTurnkey signer still gets the strategy -- paper trade, unsigned tx per\ntick. Informational rationale only (rules 5-8); the created strategy still\nruns only through the existing engine gates.\n\nWorkflow: DECIDE -> EXECUTE step -- the MCP-only closing move for\nget_strategy_suggestions; pair with backtest_strategy + get_risk_assessment\nfirst for the same guardrails any other create path gets.", "inputSchema": { "additionalProperties": false, "properties": { "agent_wallet_id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "caller_id": { "default": "", "type": "string" }, "config_overrides": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "interval_seconds": { "default": 3600, "type": "integer" }, "suggestion_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "suggestion_id", "wallet_address" ], "type": "object" }, "name": "intelligence_suggestion_approve", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Record a decision in your private, wallet-scoped journal (free write).\n\nYour durable memory on Crank: rationale, intended action, and optional\nexpectations (e.g. {\"direction\": \"up\", \"horizon\": \"24h\"}) are stored as\none opaque body only you can read back; the system later attributes\nrealised P&L from on-chain-verified fills and marks prices at\n1h/24h/7d/30d horizons. idempotency_key makes replays safe (offline\nqueues / batch agents). Link evidence via signal_ids / suggestion_id /\nstrategy_id (your own strategies only). Autonomous strategy executions\nare journaled for you automatically -- use this to add the\nagent-authored layer on top.\n\n``tx_signature`` (optional): pass the\nsignature a swap/perp/lend/stake tool just returned to link this\ndecision to its verified on-chain fill -- the proof the Layer 2\ncontribution firewall needs. Unknown signature for this wallet -> 404.\nIf omitted, the wallet's most recent CONFIRMED transaction within a\nshort window is auto-linked as a best-effort fallback -- explicit is\nstill more reliable, pass it whenever you have it.\n\nWorkflow: DECIDE step -- journal before (or as) you act; query it back\nwith journal_query / get_my_performance.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "client_platform": { "default": "", "type": "string" }, "decision_type": { "type": "string" }, "expectations": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "idempotency_key": { "default": "", "type": "string" }, "intended_action": { "default": "", "type": "string" }, "rationale": { "type": "string" }, "session_id": { "default": "", "type": "string" }, "signal_ids": { "anyOf": [ { "items": { "type": "integer" }, "type": "array" }, { "type": "null" } ], "default": null }, "strategy_id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "suggestion_id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "tx_signature": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "decision_type", "rationale" ], "type": "object" }, "name": "journal_append", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Read your own decision journal, most recent first (free read).\n\nWallet-scoped: only decisions journaled for wallet_address are ever\nreturned. Filters: window_hours (0 = all), decision_type, strategy_type,\nasset (mint/symbol as journaled), outcome_sign\n(positive|negative|zero on realised P&L), source (agent|system|human --\npass source=\"human\" to see only a manual override on this shared\naccount: human and agents act on ONE account, and every human action is\njournaled so agents can see and reconcile with it). Every returned row\ncarries its source. detail=concise returns id/type/timestamp/pnl rows\n(token-budget friendly); detail=full adds bodies, evidence refs, and\nfull outcome marks.\n\nWorkflow: ORIENT step -- recall what you decided (and what a human may\nhave overridden) before deciding again.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "decision_type": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "limit": { "default": 50, "type": "integer" }, "outcome_sign": { "default": "", "type": "string" }, "source": { "default": "", "type": "string" }, "strategy_type": { "default": "", "type": "string" }, "wallet_address": { "type": "string" }, "window_hours": { "default": 0, "type": "integer" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "journal_query", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Execute a token swap via Jupiter (non-custodial).\n\nWithout signed_transaction: returns an UNSIGNED base64 transaction for your\nwallet to sign + broadcast. With signed_transaction: broadcasts the\ncaller-signed tx and returns tx_signature. amount is in base units of\ninput_token. Includes the Crank technology service fee when a referral fee\naccount is configured -- collected ON-CHAIN via Jupiter's platformFeeBps, deducted from swap output. Swaps are NOT additionally gated by\nx402 (that would double-charge the same fee), so\npayment_header stays a no-op here (jupiter_swap is not in x402 PAID_TOOLS).\npay_in_crank is NO LONGER a no-op: the on-chain rate is now\nderived from this wallet's volume tier and $CRANK staker / pay-in-$CRANK /\nCrank Score discounts, so a discounted wallet is quoted a lower\nplatformFeeBps -- the same schedule x402 applies to perps/lend/stake.\n\nslippage_bps omitted (None) resolves to the published\nplatform default of 50 bps -- unchanged from before; the returned\nenvelope's slippage.applied_source honestly reports \"platform_default\"\nin that case rather than falsely claiming \"caller\".\n\nSECURITY: the output_token is run through multi-layer authenticity\nverification before any tx is built; an unverified/suspicious/fake token is\nblocked (UNVERIFIED_TOKEN). Set allow_unverified=true to trade an unverified\ntoken at your own risk (hard scam signals are never overridable).\n\n``venue_hint`` is ADVISORY, never\nrequired -- spot routes via Jupiter aggregation (the only spot venue\ntoday); an unknown hint raises, omitting it is unchanged from before.\n\nWorkflow: EXECUTE step -- deploy the directional/allocation leg after the risk\nphase capped the size. Non-custodial. Get a price first with get_quotes.\nSee get_trading_workflow.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying the SAME call (build or broadcast) with the same key + same args\nreplays the original result instead of re-executing -- guards against a\ntimeout-then-retry double-swap. Reuse the SAME key across the build call\nand its signed_transaction broadcast retry (they dedupe independently);\na NEW key means a genuinely new swap.\n\n``verify`` (default True): when broadcasting\n(signed_transaction supplied), await on-chain confirmation and re-read\nthe output_token balance -- the response gains a ``verification`` block\n({confirmed, slot, post_state, expected_vs_actual}). Gate follow-on\ndecisions on ``verification.confirmed``, never on tx_signature alone.\nSet False to skip for latency-sensitive callers. Verify any prior\nsignature later with the standalone ``verify_transaction`` tool.\n\nGEO GATE: when either leg is a tokenized\nsecurity this call is geo-gated (Reg S = no US persons) and OFAC-screened,\nsame control ``trade_equity`` enforces -- ``jurisdiction`` declares the\ncaller's jurisdiction once (persisted for next time), ``ip`` is the\ncaller's origin IP for the additional Reg-S IP layer. Non-security swaps\nare unaffected.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "input_token": { "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "output_token": { "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "slippage_bps": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "venue_hint": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "input_token", "output_token", "amount", "wallet_address" ], "type": "object" }, "name": "jupiter_swap", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Emergency freeze an agent wallet.\n\nSets status=killed so the policy gate refuses every subsequent value-bearing\naction. Returns confirmation + a frozen-positions count. (Turnkey scoped-key\nrevocation is handled by the deferred provisioning ticket.)", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "kill_wallet", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Borrow against deposited collateral (non-custodial).\n\nReturns an UNSIGNED base64 tx + current health factor (pre-borrow estimate).\namount in base units of borrow_token. Deposit collateral first. Past the\ndaily free tier an x402 payment_header is required. The borrowed token is\nauthenticity-verified first; set allow_unverified=true to borrow an unverified\ntoken at your own risk.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-borrowing. Reuse the SAME key across the build call and its\n``signed_transaction`` completion call -- see lend_deposit;\nthe two legs dedupe independently, so this never raises\nIDEMPOTENCY_CONFLICT.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nsee lend_deposit -- re-call with the signed tx and Crank broadcasts it,\nconfirms it on-chain, and re-reads the borrowed balance + obligation health.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "borrow_token": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "collateral_token": { "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "protocol": { "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "protocol", "collateral_token", "borrow_token", "amount", "wallet_address" ], "type": "object" }, "name": "lend_borrow", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Deposit assets to earn yield on Kamino or Marginfi (non-custodial).\n\nReturns an UNSIGNED base64 tx to sign + broadcast, plus supply APY. amount\nis in base units of token. protocol: kamino | marginfi -- pin one to keep\nexact prior behaviour. Marginfi needs marginfi_account (create via the\nsidecar). Past the daily free tier an x402 payment_header is required. The\ndeposited token is authenticity-verified first; set allow_unverified=true\nto supply an unverified token at own risk.\n\n``venue_hint`` / auto-route: pass ``protocol=\"auto\"`` (or\n``\"\"``) -- optionally with ``venue_hint`` as an advisory alias, same\nnaming as jupiter_swap/trade_equity -- to route through the SAME\nprimary+fallback health-failover the internal earn/lending trade bridge\nalready applies: an empty rate snapshot on the primary\nprotocol fails over to the configured fallback. Extends this tool instead\nof adding a separate earn_quote/trade_earn surface, so lend_deposit is now\nthe one first-class MCP path for both a pinned protocol and an\nauto-routed deposit. A router-resolved call also carries the\nsmart-contract counterparty-risk disclosure in the response\n(``disclosures``), matching the internal bridge.\n\nWorkflow: EXECUTE step (yield leg) -- supply idle stables/tokens after\ncomparing get_lending_rates; monitor with get_health_factor. See\nget_trading_workflow.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-depositing. Reuse the SAME key across the build call and its\n``signed_transaction`` completion call -- the two legs\ndedupe independently, so this never raises IDEMPOTENCY_CONFLICT; a NEW\nkey means a genuinely new deposit.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nre-call this tool with the SIGNED base64 tx and Crank broadcasts it, then\nawaits on-chain confirmation and re-reads BOTH the deposited token's\nbalance and the obligation's health -- the response carries a real\n``verification`` block ({confirmed, slot, post_state, expected_vs_actual}).\nGate follow-on borrowing on ``verification.confirmed``, never on\ntx_signature alone. verify=false skips only the confirmation wait. When\nthe build leg auto-routed (protocol=\"auto\"), pass back the SAME resolved\n``protocol`` the build response reported -- re-resolving from \"auto\"/\nvenue_hint again on the completion leg could pick a different venue if\nhealth changed between calls.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "protocol": { "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "token": { "type": "string" }, "venue_hint": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "protocol", "token", "amount", "wallet_address" ], "type": "object" }, "name": "lend_deposit", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Repay borrowed amount (non-custodial). Returns an UNSIGNED base64 tx +\ncurrent health factor. amount in base units of token. Past the daily free\ntier an x402 payment_header is required.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-repaying. Reuse the SAME key across the build call and its\n``signed_transaction`` completion call -- see lend_deposit;\nthe two legs dedupe independently, so this never raises\nIDEMPOTENCY_CONFLICT.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nsee lend_deposit -- re-call with the signed tx and Crank broadcasts it,\nconfirms it on-chain, and re-reads the repaid balance + obligation health.", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "protocol": { "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "token": { "type": "string" }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "protocol", "token", "amount", "wallet_address" ], "type": "object" }, "name": "lend_repay", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Unwind a tracked leveraged position: sell -> repay stable -> withdraw.\n\nReturns an ORDERED STEP PLAN. position_id from leverage_long. Past the daily\nfree tier an x402 payment_header is required.\n\n``jurisdiction``: closes are geo-gated too --\nsee short_open.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-unwinding the position.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "position_id": { "type": "integer" }, "slippage_bps": { "default": 50, "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "position_id", "wallet_address" ], "type": "object" }, "name": "leverage_close", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open a lending-based leveraged long by looping deposit -> borrow stable\n-> buy more -> redeposit.\n\nReturns an ORDERED STEP PLAN of UNSIGNED base64 txs, effective leverage, loop\ncount, health factor, and a position_id. amount in base units. The levered\ntoken is authenticity-verified first; set allow_unverified=true to lever an\nunverified mint at your own risk. Past the daily free tier an x402\npayment_header is required.\n\n``jurisdiction``: leverage is geo-gated too --\nsee short_open.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-opening the leveraged position.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "protocol": { "default": "kamino", "type": "string" }, "slippage_bps": { "default": 50, "type": "integer" }, "stable_token": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "target_leverage": { "type": "number" }, "token": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "token", "amount", "target_leverage", "wallet_address" ], "type": "object" }, "name": "leverage_long", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Stake SOL for a liquid-staking token (non-custodial).\n\namount in lamports. protocol: marinade | jito | blaze. Returns an UNSIGNED\nbase64 tx + the LST received + current APY. The technology service fee is\ncharged on the staked-SOL notional past the daily free tier (x402\npayment_header; set pay_in_crank for the $CRANK discount).\n\nWorkflow: EXECUTE step (yield leg) -- stake the idle slice after comparing\nget_lst_yields. Non-custodial. Monitor via portfolio_snapshot. See\nget_trading_workflow.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-staking. Reuse the SAME key across the build call and its\n``signed_transaction`` completion call -- the two legs\ndedupe independently, so this never raises IDEMPOTENCY_CONFLICT; a NEW\nkey means a genuinely new stake.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nre-call this tool with the SIGNED base64 tx and Crank broadcasts it, then\nawaits on-chain confirmation and re-reads the LST + SOL balances -- the\nresponse carries a real ``verification`` block ({confirmed, slot,\npost_state, expected_vs_actual}). Gate follow-on decisions on\n``verification.confirmed``, never on tx_signature alone. verify=false skips\nonly the confirmation wait.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "protocol": { "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "protocol", "amount", "wallet_address" ], "type": "object" }, "name": "liquid_stake", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "List a wallet's alerts -- what is currently armed. Free read.\n\nCovers both price/position alerts (set_alert) and health-factor liquidation\nalerts (set_liquidation_alert) -- one table, told apart by alert_type.\nDefault shows only ARMED alerts (active, not yet triggered) -- exactly the\nset the Celery evaluators will act on. include_triggered=True adds already-\ntripped and deactivated alerts (recent history). limit caps at 200.\n\nWorkflow: MONITOR step -- read before arming another alert so you do not\nduplicate a level that is already watched. Pairs with set_alert. See\nget_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "include_triggered": { "default": false, "type": "boolean" }, "limit": { "default": 50, "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "list_alerts", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "List all delegated session signers (active + revoked) for a wallet.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "list_session_signers", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Catalog of every available signal stream (free read).\n\nOne entry per signal source across all tiers -- on-chain collectors, free\nAPI sources, derived analyzers and external provider adapters -- with tier,\ncost-gate state (paid Tier-D gates are fail-closed and disabled by\ndefault), coverage window (earliest/latest persisted signal -- the honest\nbacktest window), effectiveness stats (graded evaluation count + correct\nrate) and a gameability class (social streams rank high -- they carry\nanti-gaming caps). Descriptive historical data only. Not financial advice.\n\nWorkflow: COMPOSE step -- enumerate streams before authoring a composite\nstrategy definition; pair with get_signals to inspect a stream's feed.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "include_inactive": { "default": true, "type": "boolean" } }, "type": "object" }, "name": "list_signal_catalog", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "List a wallet's webhook subscriptions (free read; secrets are never returned).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "list_webhooks", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Swap between two LSTs via the Sanctum router (non-custodial).\n\nfrom_lst/to_lst are mints; amount in base units. Returns an UNSIGNED base64\ntx + output amount. The technology service fee is charged on the input-LST\nnotional past the daily free tier (x402 payment_header). The acquired LST\n(to_lst) is authenticity-verified first; set allow_unverified=true to swap\ninto an unverified LST at your own risk.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-swapping. Reuse the SAME key across the build call and its\n``signed_transaction`` completion call -- see liquid_stake;\nthe two legs dedupe independently, so this never raises\nIDEMPOTENCY_CONFLICT.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nsee liquid_stake -- re-call with the signed tx and Crank broadcasts it,\nconfirms it on-chain, and re-reads both LST balances.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "from_lst": { "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "to_lst": { "type": "string" }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "from_lst", "to_lst", "amount", "wallet_address" ], "type": "object" }, "name": "lst_swap", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Cash out crypto to fiat via MoonPay (non-custodial).\n\ntoken is the crypto to sell; amount is its quantity; destination is a\nMoonPay bank_account_id the fiat is paid to. Returns offramp_id,\nestimated_fiat, and status. Past the daily free tier an x402 payment_header\nis required.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result (same\nofframp_id) instead of creating a second MoonPay sell order.", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "number" }, "caller_id": { "default": "", "type": "string" }, "destination": { "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "token": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "token", "amount", "destination" ], "type": "object" }, "name": "offramp_to_fiat", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Close a perp position, full or partial (non-custodial).\n\nclose_pct in (0, 100]. Returns an UNSIGNED base64 tx to sign + broadcast,\nplus exit price + realized P&L estimate (incl funding). Past the daily free\ntier an x402 payment_header is required.\n\n``jurisdiction``: closes are geo-gated too --\nsee perp_open_long.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-closing the position.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nsee perp_open_long -- re-call with the signed tx and Crank broadcasts it,\nconfirms it on-chain, and re-reads the position.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "close_pct": { "default": 100, "type": "number" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "position_id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "market" ], "type": "object" }, "name": "perp_close", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Current funding for a perp market (rate, period, last funding timestamp).\n\nmarket e.g. SOL-PERP. period is informational (1h/8h/24h).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "market": { "type": "string" }, "period": { "default": "1h", "type": "string" } }, "required": [ "market" ], "type": "object" }, "name": "perp_funding_rates", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Normalized funding/borrow rates across venues (venue=None aggregates).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "type": "object" }, "name": "perp_funding_rates_all", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Available Drift perp markets with price, open interest, funding, max leverage.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" } }, "type": "object" }, "name": "perp_markets", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Perp markets across venues (venue=None aggregates all routable venues).\n\ndetail=\"concise\" (default) trims each market to symbol/venue/price/\nmax_leverage (symbol is the ID to chain into place_perp_order); \"full\"\nadds base/quote/custody_tier/min_size/open_interest_usd.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "type": "object" }, "name": "perp_markets_all", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Modify an existing open Drift ORDER by order_id (non-custodial).\n\nAdjusts trigger price (TP/SL). new_leverage / add_collateral require a\nseparate collateral deposit/withdraw and are recorded for tracking. Returns\nan UNSIGNED base64 tx to sign + broadcast. Past the daily free tier an x402\npayment_header is required.\n\n``jurisdiction``: modify (changes leverage/\nexposure) is geo-gated too -- see perp_open_long.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-modifying the order.", "inputSchema": { "additionalProperties": false, "properties": { "add_collateral": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "new_leverage": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "new_sl": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "new_tp": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "order_id": { "type": "integer" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "order_id" ], "type": "object" }, "name": "perp_modify", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open a leveraged LONG perp position on Drift (non-custodial).\n\nReturns an UNSIGNED base64 transaction for your wallet to sign + broadcast,\nplus entry/liquidation/margin estimates. market e.g. SOL-PERP. size_usd is\nnotional USD; leverage up to the market max. TP/SL are informational in the\nbuild — place them as trigger orders after the position opens. The fee is\ncharged on size_usd notional past the daily free tier (x402 payment_header).\n\n``jurisdiction``: your ISO-3166-1 alpha-2\ncountry code, self-declared -- perps are geo-gated (CFTC posture: no US\npersons, unknown jurisdiction DENIED). Pass it once here (or via\n``declare_jurisdiction``/``trade_equity``) and it is remembered for 90\ndays; every perps/short/leverage call is denied until declared.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-opening the position. Reuse the SAME key across the build call and\nits ``signed_transaction`` completion call -- the two legs\ndedupe independently (the completion leg is namespaced under its own\nstorage key, matching jupiter_swap's build/broadcast pattern), so this\nnever raises IDEMPOTENCY_CONFLICT; a NEW key means a genuinely new order.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nre-call this tool with the SIGNED base64 tx and Crank broadcasts it, then\nawaits on-chain confirmation and re-reads the perp position -- the response\ncarries a real ``verification`` block ({confirmed, slot, post_state,\nexpected_vs_actual}). Gate follow-on decisions on ``verification.confirmed``,\nnever on tx_signature alone. verify=false skips only the confirmation wait.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "leverage": { "type": "number" }, "market": { "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "size_usd": { "type": "number" }, "stop_loss_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "take_profit_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "market", "size_usd", "leverage" ], "type": "object" }, "name": "perp_open_long", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open a leveraged SHORT perp position on Drift (non-custodial).\n\nSame envelope as perp_open_long, opposite direction. ``jurisdiction``, ``idempotency_key`` (optional)\nand ``signed_transaction``/``verify`` (two-phase execution):\nsee perp_open_long.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "leverage": { "type": "number" }, "market": { "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "size_usd": { "type": "number" }, "stop_loss_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "take_profit_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "market", "size_usd", "leverage" ], "type": "object" }, "name": "perp_open_short", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "List open perp positions for a wallet with live P&L.\n\nEach: market, side, size, entry/mark price, unrealized P&L (incl funding),\nliquidation price.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "perp_positions", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open perp positions for a wallet. venue=None aggregates across venues.\n\nEach position carries its venue + custody_tier. detail=\"concise\" (default)\ntrims each position to position_id/market/side/size/unrealized_pnl/venue\n(position_id is the ID to chain into close_perp_position) plus\ntpsl_triggers -- the TP/SL triggers resting on the position, each with the\nrequest_id set_perp_tpsl takes to amend or cancel it; \"full\" adds\nentry_price/current_price/leverage/liquidation_price/custody_tier.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "perp_positions_all", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open a leveraged perp position on the best/selected venue (non-custodial).\n\nside is \"long\" | \"short\". market e.g. SOL-PERP; size_usd is notional USD.\nvenue optional -- defaults to the configured primary (Jupiter Perps), with\nhealth failover to the fallback for new orders. Returns an UNSIGNED tx\n(Tier A) or a signing payload (Tier B) for your wallet to sign + broadcast,\nplus venue_name / custody_tier / settlement_token. Tier B (venue-custodied)\nvenues require acknowledge_tier_b=true after reviewing custody_disclosure.\nFee charged on size_usd notional past the daily free tier (x402).\n\n``jurisdiction``: your ISO-3166-1 alpha-2\ncountry code, self-declared -- perps are geo-gated (no US persons, unknown\njurisdiction DENIED). Declare once here (or via\n``declare_jurisdiction``/``trade_equity``) and it is remembered 90 days.\n\nWorkflow: EXECUTE step (leveraged directional leg) -- after get_venue_health /\nget_venue_risk_score clear the venue and get_risk_assessment caps the size.\nMonitor via perp_positions. See get_trading_workflow.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-opening the order. Reuse the SAME key across the build call and its\n``signed_transaction`` completion call -- the two legs\ndedupe independently, so this never raises IDEMPOTENCY_CONFLICT; a NEW key\nmeans a genuinely new order.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nre-call this tool with the SIGNED payload and Crank relays it by custody\ntier -- Tier A to Solana RPC, then awaits on-chain confirmation and\nre-reads the position on the executing venue; Tier B to the venue's own\nsubmit endpoint, which returns a venue order id (reported as\nvenue-acknowledged, since it is not an on-chain signature). Gate follow-on\ndecisions on ``verification.confirmed``, never on tx_signature alone.\n\n``venue_action`` (optional, completion leg only): the value\nthe BUILD leg recorded on ``extra['venue_action']`` -- pass it back\nalongside ``signed_transaction`` so Crank relays the bytes under the venue\naction the venue itself named (e.g. Jupiter's create-limit-order, for a\nkeeper-co-signed build that can only land via the venue's execute\nendpoint). Omit it and Crank infers the route from the signed bytes' own\nmessage header instead, which is correct but less authoritative.", "inputSchema": { "additionalProperties": false, "properties": { "acknowledge_tier_b": { "default": false, "type": "boolean" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "leverage": { "type": "number" }, "limit_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "market": { "type": "string" }, "order_type": { "default": "market", "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "side": { "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "size_usd": { "type": "number" }, "stop_loss_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "take_profit_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "venue_action": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "market", "side", "size_usd", "leverage" ], "type": "object" }, "name": "place_perp_order", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Pledge to a token launch. PLAN MODE BY DEFAULT (non-custodial).\n\n``amount`` is in pledge-mint BASE UNITS (USDC is 6dp: 1_000_000 = 1 USDC).\n\nDefault (``confirm=false``) returns ``action: \"plan\"`` -- a preview that\nevaluates every on-chain guard off-chain first (launch status, pledge\nwindow, remaining capacity, per-wallet cap) plus the anti-sybil screen and\na pro-rata allocation projection. Nothing is built and nothing moves.\n\n``confirm=true`` returns ``action: \"sign_required\"`` with an UNSIGNED\nbase64 transaction you sign with your own wallet and broadcast yourself.\nCrank never holds your keys. A pledge is irreversible once broadcast: the\non-chain refund path opens only if the raise fails its minimum.\n\nUtility token fair launch -- this commits funds to a non-custodial escrow.\nIt is not a purchase of any expectation of profit and confers no claim on\nissuer revenue. The technology service fee applies past the daily free tier\n(x402 payment_header; set pay_in_crank for the $CRANK discount).\n\n``idempotency_key`` (optional): a client-generated UUID. Retrying with the\nsame key + same args replays the original result instead of pledging twice.\n\nUS persons are blocked (Reg S-flavoured geo-posture, I4),\nand persons in Australia are blocked by a second independent layer: declare ``jurisdiction`` (ISO-3166-1 alpha-2) or rely on a stored\nattestation; unknown jurisdiction is DENIED. ``confirm=true`` additionally\nrequires ``disclosures_acknowledged=true`` -- read the mandatory\npre-pledge disclosure block (``get_ilo_details`` or a plan-mode preview)\nfirst (I2).\n\nWorkflow: EXECUTE step -- get_ilo_details, then plan-mode preview, then\nconfirm=true. Track it afterwards with get_my_pledge_status.", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "confirm": { "default": false, "type": "boolean" }, "disclosures_acknowledged": { "default": false, "type": "boolean" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "default": "", "type": "string" }, "launch_id": { "type": "integer" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "pledger_token_account": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "launch_id", "amount", "wallet_address" ], "type": "object" }, "name": "pledge_to_ilo", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Poll a Lane 2 enablement request; provisions the wallet ONLY once approved.\n\nOn approval, applies the server-enforced conservative Lane 2 default\npolicy (per-tx $50, daily $200, SOL+USDC only, 10% drawdown halt) and a\n10-execution training-wheels counter, then returns the policy READ BACK\nfrom the server -- never the intended one.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "device_code": { "type": "string" } }, "required": [ "device_code" ], "type": "object" }, "name": "poll_agent_wallet_enable", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Poll a grant-clear request; clears the AGNTA grant ONLY once approved.\n\nReturns {\"status\": \"pending\"} while waiting, {\"status\": \"expired\"} for an\nunknown/expired code (never fabricates approval), or on approval clears\nthrough the same rails clear_agnta_grant uses for a non-Lane-2 wallet.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "device_code": { "type": "string" } }, "required": [ "device_code" ], "type": "object" }, "name": "poll_agnta_grant_clear", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Complete (or re-check) an owner wallet's AgentIdentity binding from chain.\n\nThe poll half of the handshake: for an owner who signed AND submitted the\n``register_identity`` transaction themselves, this is the only call needed.\nVerifies the on-chain AgentIdentity account exactly as\nsubmit_agnta_identity_registration does and stamps ``registered`` only on\nsuccess; otherwise it returns the wallet's current stored status with\n``verified: false`` and stamps nothing.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "identity_pda": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "identity_pda" ], "type": "object" }, "name": "poll_agnta_identity_registration", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Poll a signer-authorization request; authorizes ONLY once approved.\n\nReturns {\"status\": \"pending\"} while waiting, {\"status\": \"expired\"} for an\nunknown/expired code (never fabricates approval), or on approval binds the\nsigner through the same rails authorize_session_signer uses and returns\nthe created session_signer row.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "device_code": { "type": "string" } }, "required": [ "device_code" ], "type": "object" }, "name": "poll_session_signer_authorization", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Poll a policy-loosening request; applies it ONLY once approved.\n\nReturns the policy READ BACK from the server after the write -- never the\nrequested one.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "device_code": { "type": "string" } }, "required": [ "device_code" ], "type": "object" }, "name": "poll_wallet_policy_loosening", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Full portfolio summary: positions, total value, allocation %, 24h change.\n\nPersisted as a PortfolioSnapshot for historical tracking. detail=\"concise\"\n(default) returns total_value_usd/change_24h_pct/snapshot_id + up to the\ntop 10 positions (token/symbol/usd_value -- IDs for chaining); \"full\"\nreturns every position with amount/price_usd and the complete\nallocation_pcts map, as before.\n\nWorkflow: ORIENT step -- the denominator for position sizing. Call before\nintelligence/risk so sizes are net of current holdings. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "detail": { "default": "concise", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "portfolio_snapshot", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Ranked allocation plan: intent + balances + regime + yields + ML signals (free read).\n\nOne call composes the read-only surfaces an agent would otherwise\norchestrate by hand -- lending supply APYs, LST staking yields, the\nper-asset market regime, and the ML ensemble signal -- into a ranked,\nintent-shaped plan (conservative | balanced | aggressive). Each\ndirectional entry names the exact backtest_strategy args to validate\nit BEFORE deploying, plus the follow-up tool that would act on it.\nDescriptive analytics only -- never advice, never a promise of\nresults; nothing is executed.\n\nWorkflow: INTELLIGENCE/ANALYSIS step -- call after get_market_briefing\nand before backtest_strategy / get_risk_assessment / strategy_*_create.", "inputSchema": { "additionalProperties": false, "properties": { "assets": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "caller_id": { "default": "", "type": "string" }, "intent": { "default": "balanced", "type": "string" }, "timeframe": { "default": "1h", "type": "string" }, "wallet_address": { "default": "", "type": "string" } }, "type": "object" }, "name": "propose_allocation", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Propose a DRAFT strategy template from an emerging pattern.\n\nPROPOSE-AND-APPROVE ONLY. Creates a draft template that is NOT\npublished, NOT verified and NOT eligible for cloning; an administrator\nmust explicitly approve it before it can appear in the marketplace.\nThis tool can never publish, verify, or modify an existing live\ntemplate, and never auto-applies anything. pattern_id comes from\nget_emerging_patterns; only an active, released pattern may be\nproposed. Descriptive historical observation\n-- not a recommendation, not financial advice, and not a promise of\nfuture results.\n\nWorkflow: PROPOSE step -- raise an observed emergent motif for human\nreview; approval and any publication remain a human decision.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "description": { "default": "", "type": "string" }, "name": { "default": "", "type": "string" }, "pattern_id": { "type": "string" } }, "required": [ "pattern_id" ], "type": "object" }, "name": "propose_template_update", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Publish a cloneable strategy config to the marketplace (the flywheel).\n\nconfig_template is the parameter set others clone. anonymous=true omits the\nauthor. performance_summary is a factual metrics blob -- no return promises\nare stored or surfaced (hard rule 8). backtest_run_id attaches a verified\nbacktest (on-chain attestation hash + leaderboard ranking). Equity\n(tokenized-security) strategies are excluded. Read/control-plane,\nfree.", "inputSchema": { "additionalProperties": false, "properties": { "anonymous": { "default": false, "type": "boolean" }, "author_wallet_address": { "default": "", "type": "string" }, "backtest_run_id": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "caller_id": { "default": "", "type": "string" }, "config_template": { "additionalProperties": true, "type": "object" }, "description": { "default": "", "type": "string" }, "name": { "type": "string" }, "performance_summary": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "strategy_type": { "type": "string" } }, "required": [ "strategy_type", "name", "config_template" ], "type": "object" }, "name": "publish_strategy", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Register/refresh an agent's discovery profile in the Crank registry.\n\ncapabilities is a subset of swap|perps|lending|staking|strategies|signals|\nequity|onramp; supported_protocols e.g. [\"mcp\",\"a2a\",\"x402\"]. Idempotent on\nwallet_address (a PUBLIC key -- non-custodial). This is how other agents find\nyou via the A2A Agent Card + Solana Agent Registry.", "inputSchema": { "additionalProperties": false, "properties": { "a2a_card_url": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "capabilities": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "contact": { "default": "", "type": "string" }, "description": { "default": "", "type": "string" }, "display_name": { "default": "", "type": "string" }, "mcp_endpoint": { "default": "", "type": "string" }, "supported_protocols": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "version": { "default": "1.0.0", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "register_agent", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Register/replace/clear the AGNTA counterparty allow-set for the\ncaller's opted-in DelegationGrant (non-custodial control plane).\n\nPersists to Django so the set survives an MCP process restart and is\nvisible to every process -- the follow-up to 's process-local\n``InMemoryCounterpartySetResolver``. ``wallet_address`` must belong to an\n``AgentWallet`` with a non-blank ``agnta_grant_pda`` already configured\n(opting in is a separate step, out of scope here); the target grant_pda\nis always resolved from that wallet, never caller-supplied. ``members``\nis a list of base58 32-byte destination pubkeys the grant's\n``counterparty_root`` should allow -- pass an EMPTY list to CLEAR the\nregistered set, after which every transfer-class call naming an on-chain\ndestination for this grant fails closed.\n\n``expected_root`` (hex, optional but STRONGLY recommended): compare\nagainst the grant's live on-chain ``counterparty_root`` (hex-encoded)\nbefore calling this -- when given, a set that does not commit to it is\nrefused (INVALID_PARAMS) rather than silently registered, which would\notherwise surface later as a confusing AGNTA_GRANT_COUNTERPARTY_DENIED on\nan unrelated transfer.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "expected_root": { "default": "", "type": "string" }, "members": { "items": { "type": "string" }, "type": "array" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "members" ], "type": "object" }, "name": "register_counterparty_set", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Register an agent integrator by its payout wallet -- lands PENDING.\n\nThe Jupiter-integrator self-serve onboarding step. The profile earns NOTHING\nuntil an admin approves it and sets its fee-share (anti-gaming whitelist).\nIdempotent on ``wallet_address``. Returns the integrator stats.", "inputSchema": { "additionalProperties": false, "properties": { "agent_id": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "contact_email": { "default": "", "type": "string" }, "name": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "register_integrator", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "First-touch bind an onboarded agent wallet to an approved integrator.\n\nFirst-touch wins: a wallet already attributed to any integrator keeps that\nbinding. Requires the integrator be approved; rejects a self-referral.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "integrator_wallet_address": { "type": "string" }, "referred_wallet_address": { "type": "string" } }, "required": [ "integrator_wallet_address", "referred_wallet_address" ], "type": "object" }, "name": "register_referrer", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Register (or reactivate) a lifecycle-event webhook for a wallet (free control-plane write).\n\nevent_types is a non-empty subset of: pre_trade (advisory only, never\nblocks a trade), post_trade, policy_violation, drawdown_warning,\nstrategy_executed. url is your https(s) receiving endpoint. secret is\nYOUR OWN HMAC-SHA256 signing secret (8-128 chars) -- Crank never sends\nor stores platform key material here (hard rule 1); you use it to\nverify the `X-Crank-Signature` header on every delivered event (see\ndocs/WEBHOOKS.md). Re-registering the same (wallet_address, url) pair\nupdates its event_types/secret and reactivates it if it was\nauto-disabled after repeated delivery failures.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "event_types": { "items": { "type": "string" }, "type": "array" }, "secret": { "type": "string" }, "url": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "event_types", "url", "secret" ], "type": "object" }, "name": "register_webhook", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Self-report an MCP-registry install/discovery event.\n\nProducer for the ``registry_install`` inbound-artifact leg that\n``growth_metrics.organic_integration_candidates`` already\nconsumes: call this once, with your own stable ``caller_id``, after your\nserver installs/discovers Crank via an MCP registry listing (Smithery,\nPulseMCP, the official MCP registry). Writes a synthetic marker row --\nmoves no funds, never fee-gated, and is idempotent per-process (a repeat\ncall for the same caller_id is a documented no-op).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" } }, "type": "object" }, "name": "report_registry_install", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open the browser-confirmation handshake to clear a Lane 2 wallet's\nAGNTA grant cap.\n\nCall this when clear_agnta_grant refuses with\nBROWSER_CONFIRMATION_REQUIRED. Does NOT clear the grant -- returns a\nconfirmation URL like request_wallet_policy_loosening; the wallet's OWNER\nmust approve in their own browser (never in-chat). Poll with\npoll_agnta_grant_clear(device_code) once approved.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "request_agnta_grant_clear", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Re-enter an AGNTA AgentIdentity binding that has not reached ``registered``.\n\nBranches on SIGNING CAPABILITY, not on a status label: an OWNER /\nSessionSigner wallet is moved to ``pending`` and handed a fresh UNSIGNED\n``register_identity`` instruction -- the OWNER signs it with their own\nwallet (no key material ever reaches Crank, hard rule 1) and then calls\nsubmit_agnta_identity_registration, or submits it themselves and calls\npoll_agnta_identity_registration. A TURNKEY-AUTONOMOUS wallet re-runs the\nreal build + sign + submit instead. An already-``registered`` wallet is a\nno-op.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "request_agnta_identity_registration", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open the browser-confirmation handshake to authorize a session signer.\n\nThe ONLY way to mint a session signer -- authorize_session_signer always\nrefuses with BROWSER_CONFIRMATION_REQUIRED for every wallet. Does NOT authorize the signer -- returns a confirmation URL like\nenable_agent_wallet; the wallet's OWNER must approve in their own browser\n(wallet-signature gated, never in-chat). Poll with\npoll_session_signer_authorization(device_code) once approved.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "capabilities": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "expires_at": { "default": "", "type": "string" }, "label": { "default": "", "type": "string" }, "signer_pubkey": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "signer_pubkey" ], "type": "object" }, "name": "request_session_signer_authorization", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open the browser-confirmation handshake to loosen a Lane 2 wallet's policy.\n\nCall this when set_wallet_policy refuses a change with\nBROWSER_CONFIRMATION_REQUIRED. Does NOT apply the policy -- returns a\nconfirmation URL like enable_agent_wallet. Poll with\npoll_wallet_policy_loosening(device_code) once the user approves.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "policies": { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "policies" ], "type": "object" }, "name": "request_wallet_policy_loosening", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Instantly revoke a delegated session signer (non-custodial control plane).\n\nSingle atomic DB UPDATE -- the gate resolves the row fresh on every call\nwith no cache, so this is enforced on the very next call using\nsigner_pubkey. No TTL/cache window.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "signer_pubkey": { "type": "string" } }, "required": [ "signer_pubkey" ], "type": "object" }, "name": "revoke_session_signer", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Keyword search over the full Crank tool catalog (progressive disclosure).\n\nRead-only, free, never gated. Purpose-built for a discovering agent\nthat does not want to load the full tool catalogue into context just\nto find the one it needs ( R1 -- the Solana\nAgent Kit V1 failure mode: 60+ tools in context caused tool-selection\nhallucinations). Pass a keyword or short phrase (e.g. \"perp funding\nrate\", \"stake sol\", \"referral\"); matches rank by keyword overlap\nagainst each tool's name + description.\n\nReturns up to ``limit`` (default 10, max 50) results, each\n``{name, purpose, toolset}`` -- ``purpose`` is a one-line summary\n(call the tool itself, or get_trading_workflow, for the full\npicture), and ``toolset`` names which of the ten named toolsets\n(market_data, spot, perps, lending_staking, portfolio, strategies,\nintelligence, rewards_growth, wallet_admin, support) the tool belongs\nto. No tool is renamed or hidden by this search -- it is purely a\ndiscovery aid.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "limit": { "default": 10, "type": "integer" }, "query": { "type": "string" } }, "required": [ "query" ], "type": "object" }, "name": "search_tools", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Send tokens to an X handle via a claimable crank.ing link (non-custodial).\n\nLocks ``amount`` (base units) of ``token`` (mint) from ``sender_wallet`` into\nthe on-chain claim escrow against a fresh claim code, and returns an UNSIGNED\nbase64 transaction for the sender to sign + broadcast, plus the\ncrank.ing/{code} claim link and the claim_code (the bearer secret to embed in\nthe announcement tweet). Whoever presents the code claims the tokens and\nbinds ``referral`` on their first claim. ``expiry_days`` (optional, default 7,\nrange 1-90) sets the claim window; unclaimed tokens are returned to the sender\nafter expiry. Anti-abuse gated: sender account age, verified wallet,\nper-sender daily limit. platform: x.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result (same\nclaim_code/link) instead of locking a second escrow.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "expiry_days": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "idempotency_key": { "default": "", "type": "string" }, "platform": { "default": "x", "type": "string" }, "recipient_handle": { "type": "string" }, "referral": { "default": "", "type": "string" }, "sender_wallet": { "type": "string" }, "token": { "type": "string" } }, "required": [ "recipient_handle", "amount", "token", "sender_wallet" ], "type": "object" }, "name": "send_token_social", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Opt a wallet into an AGNTA DelegationGrant spend/scope cap\n(non-custodial control plane).\n\nValidates grant_pda decodes as a base58 32-byte address, the on-chain\naccount exists and decodes as a DelegationGrant, it is not revoked and\nnot expired, and its delegate matches wallet_address -- every failure\nraises INVALID_PARAMS with a distinct message. Adds an ADDITIONAL cap\nenforced alongside (never replacing) WalletPolicy on every subsequent\nvalue-bearing call for this wallet -- always TIGHTENS enforcement, so it\napplies directly for every wallet, Lane 2 included.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "grant_pda": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "grant_pda" ], "type": "object" }, "name": "set_agnta_grant", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a price/position alert checked every 60s by Celery beat.\n\nalert_type: price_above | price_below | position_change. token is a mint\naddress. Optional webhook_url is POSTed when the alert fires.\n\nFree (no technology service fee) -- a control-plane write, moves no funds\nand has no transaction notional.\n\nWorkflow: MONITOR step -- arm after executing so a tripped level loops you back\nto the risk/execute phase. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "alert_type": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "threshold": { "type": "number" }, "token": { "type": "string" }, "wallet_address": { "type": "string" }, "webhook_url": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "required": [ "wallet_address", "token", "alert_type", "threshold" ], "type": "object" }, "name": "set_alert", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Arm a liquidation alert: notify when a lending obligation's health factor\nfalls to or below threshold.\n\nprotocol: kamino | marginfi (marginfi_account required for marginfi).\nthreshold is the HF level (e.g. 1.2 warns before the <1.0 liquidation\npoint). Evaluated every 30s by Celery beat; webhook_url is POSTed on trip.\n\nWorkflow: MONITOR step -- arm after opening a leveraged/borrow position so a\ndeteriorating obligation loops you back to repay/de-risk. Pairs with\nget_health_factor. See get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "protocol": { "type": "string" }, "threshold": { "type": "number" }, "wallet_address": { "type": "string" }, "webhook_url": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "required": [ "wallet_address", "protocol", "threshold" ], "type": "object" }, "name": "set_liquidation_alert", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Opt in/out of the wake-on-condition worker.\n\nDefault OFF. When opted in, a triggered alert may run a metered\nbackground check (Haiku triage, escalating to Sonnet only if worth a\ncloser look) and propose one action. daily_wake_budget (default 10, 1-500)\nhard-caps metered wakes per day. The worker never executes -- every\nproposal is approved in your own wallet. See get_ooda_status for wake\nhistory including skipped wakes.\n\nUsage-vs-fee-revenue kill threshold: wakes\nauto-suspend if inference spend over kill_window_days (default 30 days)\nexceeds kill_threshold_ratio (default \"0.5\") of attributed fee revenue.\nkill_threshold_enabled lets you disable the check for this wallet;\nkill_threshold_ratio is a decimal string. All three are optional -- omit\nto leave the existing/default value untouched. See get_ooda_status for\nwhether/why a wallet was auto-killed (kill_switched_at, kill_reason).\n\nWorkflow: consent step -- run once (or to change budget/kill config)\nbefore wakes can fire; check get_ooda_status afterward to confirm state.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "daily_wake_budget": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "kill_threshold_enabled": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "kill_threshold_ratio": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "kill_window_days": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "opted_in": { "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "opted_in" ], "type": "object" }, "name": "set_ooda_consent", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Change an agent wallet's session permission mode (non-custodial control plane).\n\nPorts Claude Code's plan/acceptEdits/bypassPermissions ladder to a wallet\nwith signing power. mode: observe (deny every mutating tool outright,\nPERMISSION_MODE_BLOCKED) | propose (mutating tools return a PROPOSAL\nenvelope -- proposal_id + params + summary -- instead of executing;\napprove within the TTL via approve_proposal) | auto_within_policy (execute\nimmediately, still capped by every configured WalletPolicy -- the pre-R9\ndefault). Also settable inline via set_wallet_policy's permission_mode\nparam. The transition is logged as an AgentTransaction audit row.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "mode": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "mode" ], "type": "object" }, "name": "set_permission_mode", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Set, amend or cancel a take profit / stop loss on an ALREADY-OPEN perp position (non-custodial).\n\nplace_perp_order can attach TP/SL only inline on the order that OPENS a\nposition; this adds one to a position that is already open.\nCurrently supported on Jupiter Perps (position_id = the position pubkey,\nas returned by perp_positions_all); other venues are refused.\n\nAt least one of take_profit_price / stop_loss_price is required. size_pct\nin (0, 100] is how much of the position the trigger closes. Both are\npassed through exactly as given -- Crank never chooses or adjusts a\ntrigger price or size. Returns an UNSIGNED transaction to sign; Crank\nnever signs.\n\n``jurisdiction``: geo-gated like every perps write,\nincluding the AU block -- see place_perp_order.\n\n``idempotency_key`` (optional): see cancel_perp_order -- reuse the same key\nacross the build call and its ``signed_transaction`` completion call.\n\n``signed_transaction`` / ``verify`` (two-phase execution): see\nplace_perp_order. A TP/SL moves no position when set, so confirming the\nsignature landed IS the verification.\n\n``venue_action`` (optional, completion leg only): pass back the build\nleg's ``extra['venue_action']`` (Jupiter's create-tpsl / update-tpsl, or\nNone when the caller can broadcast itself) so the signed bytes are relayed\nthrough the venue's own execute endpoint when the build needs it.\n\nAMEND / CANCEL a resting trigger: read its ``request_id``\noff perp_positions_all (positions[].tpsl_triggers[].request_id), then call\nthis tool with ``request_id`` and either ``trigger_price`` (amend -- moves\nthe trigger to that price) or ``cancel=True`` (cancel it). position_id and\ntake_profit_price/stop_loss_price are not used in those modes, and mixing\nthem with request_id is refused. Same gates (including the AU block), same\ntwo-phase flow -- pass the same request_id / cancel on the completion call.", "inputSchema": { "additionalProperties": false, "properties": { "acknowledge_tier_b": { "default": false, "type": "boolean" }, "caller_id": { "default": "", "type": "string" }, "cancel": { "default": false, "type": "boolean" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "position_id": { "default": "", "type": "string" }, "request_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "size_pct": { "default": 100, "type": "number" }, "stop_loss_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "take_profit_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "trigger_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "venue_action": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "set_perp_tpsl", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Write a new version of the wallet's portfolio charter (free control-plane write).\n\nCreates a new active version -- the prior version stays in history,\nnever deleted (versioned mandate, not an in-place overwrite).\nrisk_band is one of conservative|balanced|aggressive. banned_tokens\nmerge into AgentWallet.evaluate_trade as an ADDITIONAL deny source\nalongside WalletPolicy.banned_tokens -- an active WalletPolicy always\nwins when it is the stricter rule; a charter can never loosen an\nexisting policy, and a conflict comes back in the response's\n`warnings` (logged server-side, never silently dropped).\ntarget_allocations is {token: percent}, must sum to <=100.\nobjectives/cadence are free-form parameters -- never phrase them as\nreturn promises (hard rules 5-8).\n\nSetting an escalation_webhook mints a platform-generated\nescalation_webhook_secret used to HMAC-SHA256-sign every escalation\nPOST (X-Crank-Signature over \"{timestamp}.{body}\"). The RAW secret is\nreturned exactly once -- in this write's response -- so the receiver\ncan be configured; every later read returns it masked. It is carried\nforward unchanged when the URL is unchanged, rotated automatically\nwhen the URL changes, and rotated on demand with\nrotate_escalation_secret=true. It is a receiver-authentication\ncredential, never wallet key or seed material (hard rule 1).\n\nWorkflow: ORIENT step 0 -- set once at the start of a relationship\nwith an agent/wallet; strategies read it on every execute_strategy\ntick (see get_trading_workflow).", "inputSchema": { "additionalProperties": false, "properties": { "banned_tokens": { "anyOf": [ { "items": {}, "type": "array" }, { "type": "null" } ], "default": null }, "body_markdown": { "default": "", "type": "string" }, "cadence": { "default": "", "type": "string" }, "caller_id": { "default": "", "type": "string" }, "escalation_webhook": { "default": "", "type": "string" }, "max_position_pct": { "default": null, "title": "Max Position Pct" }, "objectives": { "default": "", "type": "string" }, "risk_band": { "default": "", "type": "string" }, "rotate_escalation_secret": { "default": false, "type": "boolean" }, "target_allocations": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "set_portfolio_charter", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Configure the caller's own trading limits and rules on an agent wallet.\n\npolicies: a list of {policy_type, value, enabled?} objects. policy_type is\none of max_trade_size {\"usd\"} | daily_limit {\"usd\"} | approved_tokens\n{\"tokens\"} | banned_tokens {\"tokens\"} | position_limit {\"usd\"} | kill_switch\n{\"active\"} | drawdown_limit {\"max_pct\"} | max_daily_loss {\"usd\"} |\ntrade_velocity {\"max_per_hour\", \"max_per_day\"} | venue_allowlist\n{\"venues\"}. Upserts by policy_type; returns the full updated policy set.\n(Perp leverage cap is a separate follow-up, -- not a\npolicy_type here.) On a Lane 2 wallet, a change that would LOOSEN a\nserver-enforced default raises BROWSER_CONFIRMATION_REQUIRED -- call\nrequest_wallet_policy_loosening instead.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "policies": { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "policies" ], "type": "object" }, "name": "set_wallet_policy", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Pre-filled post for a journal card, ready to publish (free read).\n\nReturns the same card as get_journal_card plus a platform-shaped share\npayload: post text within the platform's character limit, the public\ncard URL, and a compose-intent URL. ``platform`` is x | farcaster |\ngeneric.\n\nThe copy is about YOUR process -- what your agent decided, that the\nrationale was written down before the outcome, and that the record is\ncheckable on-chain. It never states or implies a return.\n\nTHIS CALL PUBLISHES THE DECISION. Your journal is private by default;\ncalling this marks THIS decision publicly readable at its card URL so\nthe link in the post resolves for anyone (and for answer engines).\nNothing else is published -- not your other decisions, not amounts,\nnot your journal body unless include_rationale=true. Reviewing with\nget_journal_card publishes nothing.\n\nWorkflow: SHARE step -- get_journal_card to review, this to publish.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "decision_id": { "type": "string" }, "include_rationale": { "default": false, "type": "boolean" }, "platform": { "default": "x", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "decision_id" ], "type": "object" }, "name": "share_journal_card", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Close a tracked short: buy token -> repay loan -> withdraw collateral.\n\nReturns an ORDERED STEP PLAN + exit price. short_id from short_open. Past\nthe daily free tier an x402 payment_header is required.\n\n``jurisdiction``: closes are geo-gated too --\nsee short_open.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-closing the short.", "inputSchema": { "additionalProperties": false, "properties": { "buy_with_amount": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "short_id": { "type": "integer" }, "slippage_bps": { "default": 50, "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "short_id", "wallet_address" ], "type": "object" }, "name": "short_close", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Open a lending-based short: deposit collateral -> borrow token -> sell.\n\nReturns an ORDERED STEP PLAN of UNSIGNED base64 txs to sign + broadcast in\nsequence, plus entry price + health factor + a short_id for tracking. All\namounts in base units. The shorted token is authenticity-verified first; set\nallow_unverified=true to short an unverified mint at your own risk. Past the\ndaily free tier an x402 payment_header is required.\n\n``jurisdiction``: your ISO-3166-1 alpha-2\ncountry code, self-declared -- synthetic shorting is geo-gated (no US\npersons, unknown jurisdiction DENIED). Declare once here (or via\n``declare_jurisdiction``/``trade_equity``/perps tools) and it is\nremembered 90 days.\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-opening the short.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "borrow_amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "collateral_amount": { "type": "integer" }, "collateral_token": { "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "protocol": { "default": "kamino", "type": "string" }, "slippage_bps": { "default": 50, "type": "integer" }, "token_to_short": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "token_to_short", "collateral_token", "collateral_amount", "borrow_amount", "wallet_address" ], "type": "object" }, "name": "short_open", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "List open shorts for a wallet with entry price + health factor.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "short_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Live reachability probe against the deployed execution sidecar.\n\nThin wrapper around ``sidecar_service.is_configured``/``healthcheck``. Runs the probe from the SERVER's own network path, which a\nlocal ``curl $SIDECAR_URL/health`` cannot do: that only proves the caller's\nown shell can reach a sidecar, never whether the deployed mcp.crank.ing\nserver can.\n\nUnconfigured (``SIDECAR_URL`` unset) raises a structured CONFIG_ERROR with\nNO network attempt -- feature-detected first via ``is_configured``.\nConfigured but unreachable returns an OK envelope with\n``reachable: False`` -- distinct from \"not configured\" -- so a caller can\ntell \"we never tried\" apart from \"we tried and it's down\".\n\nFREE read, never gated (never in x402 PAID_TOOLS): booleans/counts/hosts\nonly, no secret ever leaves this tool -- presence-only, never\n``config.SIDECAR_AUTH_TOKEN`` itself.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" } }, "type": "object" }, "name": "sidecar_health", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Backtest a strategy with an S/R config block (read-only simulation).\n\nRuns the existing backtest engine with strategy_type (default\n\"support_resistance\": bounce-long off detected support, exit on a support\nbreak or resistance-fail; on spot a SHORT signal is exit-to-flat) and\nmerges the validated sr_config into params[\"sr\"]. asset is a token mint;\ntimeframe one of 1m/5m/15m/1h/4h/1d; start_date/end_date ISO-8601. Returns\nthe standard performance metrics plus persisted SUPPORT_RESISTANCE signals\ncarrying zone metadata. Read-only simulation -- no fee, no on-chain action,\nnot financial advice (DYOR).\n\nWorkflow: SIMULATE step -- validate an S/R setup on history before risking\ncapital; feeds get_risk_assessment -> sr_configure_strategy. See\nget_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "end_date": { "type": "string" }, "fee_bps": { "default": 75, "type": "integer" }, "initial_capital": { "default": 10000, "type": "number" }, "params": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 30, "type": "integer" }, "slippage_model": { "default": "fixed", "type": "string" }, "sr_config": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "start_date": { "type": "string" }, "strategy_type": { "default": "support_resistance", "type": "string" }, "timeframe": { "type": "string" }, "wallet_address": { "default": "", "type": "string" } }, "required": [ "asset", "timeframe", "start_date", "end_date" ], "type": "object" }, "name": "sr_backtest", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Attach an S/R config block to YOUR OWN strategy (ownership-checked).\n\nPersists an `sr` param block (SRConfig knobs: sensitivity, sources,\nlookback, swing_window, zone_width_bps, merge_tolerance_bps, min_touches,\nmin_strength, max_zones_per_side, manual_levels, liquidity_weight_k) onto\nthe caller's own strategy params. The strategy must belong to\nwallet_address -- configuring someone else's strategy is refused.\nStrategies without an `sr` block behave exactly as before (back-compat).\nUser/agent-owned configuration only: you own and control the strategy; the\nplatform never exercises discretion (DYOR). No key handling, no fee.\n\nWorkflow: DECIDE step -- after sr_detect_levels + sr_backtest confirm the\nlevel picture, store the tuned config on the strategy. See\nget_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "sr_config": { "additionalProperties": true, "type": "object" }, "strategy_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "strategy_id", "wallet_address", "sr_config" ], "type": "object" }, "name": "sr_configure_strategy", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Multi-timeframe support/resistance zones + liquidity bands (read-only).\n\nDetects S/R zones per timeframe from recent OHLCV (swing highs/lows, floor\npivots, Fibonacci retracement, volume-profile clusters, optional manual\nlevels), merges them across timeframes with a confluence multiplier, and\nweights zone strength by overlapping candle-volume liquidity-band depth.\nasset is a token mint; timeframes default [\"1h\",\"4h\",\"1d\"]; lookback\ncandles per timeframe (capped at 500); sources subset of swing / pivot /\nfibonacci / volume_profile / price_impact / manual; sensitivity 0-1 (higher\n= more zones); zone_width_bps sets the band half-width; manual_levels adds\ncaller-supplied override prices. Returns zones (supports / resistances /\npivots with price, band, strength, touches, sources, timeframes) plus\nliquidity_bands. Computed reference levels only -- not financial advice,\nnot a trade instruction (DYOR). No wallet, no fee, no on-chain action.\n\nWorkflow: INTELLIGENCE step -- the level picture behind sr_backtest +\nsr_configure_strategy; pair with get_indicators + detect_regime. See\nget_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "asset": { "type": "string" }, "caller_id": { "default": "", "type": "string" }, "lookback": { "default": 200, "type": "integer" }, "manual_levels": { "anyOf": [ { "items": { "type": "number" }, "type": "array" }, { "type": "null" } ], "default": null }, "sensitivity": { "default": 0.5, "type": "number" }, "sources": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "timeframes": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "zone_width_bps": { "default": 20, "type": "integer" } }, "required": [ "asset" ], "type": "object" }, "name": "sr_detect_levels", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create an arb strategy -- cross-venue price-discrepancy convergence (APPROXIMATE).\n\nReads a live cross-venue spread each tick (task-sourced from the Jupiter\nquote corpus vs on-chain price) or falls back to a transparent PROXY\n(deviation below a short EMA) when unavailable. Enters when the spread\nclears ``entry_spread_pct`` and flat; exits when it reverts to\n``exit_spread_pct``. The simultaneous two-venue fill is collapsed to one\nleg (flagged ``approximate``). Market-neutral: no direction params exposed\n(regime is read directly, not adapted).\n\n``risk``: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "ema_period": { "default": 12, "type": "integer" }, "entry_spread_pct": { "default": 0.004, "type": "number" }, "exit_spread_pct": { "default": 0, "type": "number" }, "interval_seconds": { "default": 60, "type": "integer" }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "target_token": { "type": "string" }, "usd_per_trade": { "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_trade" ], "type": "object" }, "name": "strategy_arb_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a basis-trade strategy -- funding-harvest perp SHORT leg (APPROXIMATE).\n\nRoutes the perp leg through the multi-venue VENUE ADAPTER (hard rule 2). A\nlive delta-neutral basis trade is long spot + short perp harvesting\nfunding; this executor opens/manages only the perp SHORT leg (the spot\nlong that makes the book delta-neutral is held separately by the caller)\n-- flagged ``approximate`` + ``funding_not_modeled`` (funding PnL itself is\nnot simulated live). While funding is favourable (> ``min_funding``) and\nflat, opens the short sized ``usd_per_trade`` at ``leverage``; closes when\nfunding decays to <= ``min_funding``. Only an asset with a mapped perp\nmarket (currently SOL) can open. A Tier B (custodied) venue needs\n``acknowledge_tier_b=true``.\n\n``risk``: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "acknowledge_tier_b": { "default": false, "type": "boolean" }, "funding_lookback": { "default": 24, "type": "integer" }, "interval_seconds": { "default": 300, "type": "integer" }, "leverage": { "default": 1, "type": "number" }, "min_funding": { "default": 0, "type": "number" }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "target_token": { "type": "string" }, "usd_per_trade": { "type": "number" }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_trade" ], "type": "object" }, "name": "strategy_basis_trade_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Stop a strategy (sets status=stopped; it will not be dispatched again).", "inputSchema": { "additionalProperties": false, "properties": { "strategy_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "strategy_id", "wallet_address" ], "type": "object" }, "name": "strategy_cancel", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a composite strategy from a validated definition.\n\nSame non-custodial create path as the other 16 strategy types: the wallet\nholds its own keys; a wallet without a Turnkey signer receives an unsigned\ntransaction per tick for the owner to sign. ``mode`` defaults to LIVE\n(recorded on the config; a paper mode annotation is informational until the\nmanaged-signing epic lands). Recommended: run compose_strategy +\nbacktest_strategy on the definition FIRST -- historical results are not\npredictive; DYOR.", "inputSchema": { "additionalProperties": false, "properties": { "definition": { "additionalProperties": true, "type": "object" }, "interval_seconds": { "default": 300, "type": "integer" }, "mode": { "default": "live", "type": "string" }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "definition" ], "type": "object" }, "name": "strategy_composite_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a copy-wallet strategy -- mirrors a tracked wallet's entries/exits.\n\n``tracked_wallet`` is the Solana address to mirror (its confirmed on-chain\nbuy/sell actions are sourced each tick); ``usd_per_buy`` is the default\nmirror size (scaled by ``size_multiplier``) applied when the tracked wallet\nbuys. APPROXIMATE: no full per-fill replication (every execution is flagged\n``approximate``).\n\n``risk`` / direction params: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "interval_seconds": { "default": 60, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "size_multiplier": { "default": 1, "type": "number" }, "slippage_bps": { "default": 50, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "target_token": { "type": "string" }, "tracked_wallet": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "usd_per_buy": { "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_buy" ], "type": "object" }, "name": "strategy_copy_wallet_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a dollar-cost-average strategy buying ``usd_per_buy`` of target each interval.\n\n``risk`` (optional) overrides the safe-default risk limits:\n``max_position_pct`` / ``max_portfolio_exposure_pct`` / ``max_single_loss_pct``\n/ ``max_drawdown_pct`` / ``max_daily_loss_pct`` (percent; <=0 disables a guard).\n\nDirection (optional, all deterministic signals -- DYOR): ``direction_mode``\n(auto | long_only | short_only | manual; default auto = follow the market\nregime, reducing exposure in a bear instead of accumulating), ``allow_short``\n(enable real shorts via the configured perps venue), ``regime_override`` (force\nbull | bear | range | volatile instead of trusting detection).\n\nWorkflow: EXECUTE step -- stand up a recurring strategy after backtest_strategy\nvalidates it and get_risk_assessment sets the guards; track via strategy_status.\nAn agent wallet without a Turnkey signer = paper-trade (unsigned tx per tick).\nSee get_trading_workflow.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "interval_seconds": { "default": 86400, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "smart": { "default": false, "type": "boolean" }, "source_token": { "default": "USDC", "type": "string" }, "target_token": { "type": "string" }, "usd_per_buy": { "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_buy" ], "type": "object" }, "name": "strategy_dca_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create an equity dollar-cost-average strategy (tokenized equities / xStocks).\n\nShares the DCA executor -- identical mechanics/config to\n``strategy_dca_create`` -- tagged ``equity_dca`` because ``target_token`` is\nexpected to be a tokenized-equity mint. SEC posture: DCA is a\nMECHANICAL, user-configured strategy (not discretionary), so it stays\nautonomous even on a security target -- the per-execution confirmation gate\nonly applies to the discretionary types (momentum / sentiment). Equity\nclassification still drives geo-gating + disclaimers at execution; call\nasset_classification / get_disclaimers first.\n\n``risk`` / direction params: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "interval_seconds": { "default": 86400, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "smart": { "default": false, "type": "boolean" }, "source_token": { "default": "USDC", "type": "string" }, "target_token": { "type": "string" }, "usd_per_buy": { "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_buy" ], "type": "object" }, "name": "strategy_equity_dca_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a hedge strategy -- an exit trigger that unwinds a held position.\n\nShares the stop-loss executor -- identical config/mechanics to\n``strategy_stoploss_create`` -- framed as an active risk-offset trigger: set\n``stop_loss_pct`` / ``trailing`` to shed exposure on an adverse move, or\n``take_profit_pct`` to lock in a favourable one. At least one of\n``stop_loss_pct`` / ``take_profit_pct`` / ``trailing`` must be set.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "entry_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "interval_seconds": { "default": 60, "type": "integer" }, "position_amount": { "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "stop_loss_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "take_profit_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "target_token": { "type": "string" }, "trailing": { "default": false, "type": "boolean" }, "trailing_distance_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "position_amount" ], "type": "object" }, "name": "strategy_hedge_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "List a wallet's strategies (newest first, capped).\n\n``detail``: \"concise\" (default) trims each row to\nstrategy_id/strategy_type/status -- the IDs needed to chain into\nstrategy_status/strategy_modify/strategy_cancel/strategy_pause/\nstrategy_resume; \"full\" also includes schedule/next_execution_at, as\nbefore. An unrecognised value falls back to concise (never errors).", "inputSchema": { "additionalProperties": false, "properties": { "detail": { "default": "concise", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "strategy_list", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a market-make strategy -- two-sided spread capture (APPROXIMATE).\n\nNo live order book -- SYNTHESISES a spread from realised volatility around\na rolling mid: a \"filled bid\" (price a half-spread below mid) buys, a\n\"filled ask\" (above mid) sells (up to held inventory). Market-neutral:\nPAUSES in a trending (bull/bear) regime instead of adapting direction (a\nmaker gets run over by a directional move) -- read directly inside the\nexecutor, so no direction params are exposed here.\n\n``risk``: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "base_spread_pct": { "default": 0.002, "type": "number" }, "interval_seconds": { "default": 60, "type": "integer" }, "max_levels": { "default": 5, "type": "integer" }, "mid_period": { "default": 20, "type": "integer" }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "spread_lookback": { "default": 20, "type": "integer" }, "target_token": { "type": "string" }, "usd_per_quote": { "type": "number" }, "vol_spread_mult": { "default": 1, "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_quote" ], "type": "object" }, "name": "strategy_market_make_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Edit a running strategy's parameters IN PLACE -- no cancel + recreate.\n\nReact to a fresh signal by retuning the strategy you already own: the\nexecution history, cost-basis ledger and position state all survive, and\nthere is no window where the strategy is gone. The live executor picks the\nnew config up on its NEXT tick; a tick already in flight finishes against\nthe config it loaded (it writes only runtime state, never config, so the\ntwo can never clobber each other).\n\nScoped to the caller's own wallet (hard rule 1 -- non-custodial: this edits\na row the owner already controls; nothing here holds keys, signs or moves\nfunds).\n\nArgs (all optional -- supply at least one):\n ``config_updates``: strategy-config keys to set, merged over the existing\n config (e.g. ``{\"usd_per_buy\": 25, \"stop_loss_pct\": 0.08}``).\n ``remove_keys``: config keys to drop back to the executor's default.\n ``risk``: retune the risk limits -- ``max_position_pct`` /\n ``max_portfolio_exposure_pct`` / ``max_single_loss_pct`` /\n ``max_drawdown_pct`` / ``max_daily_loss_pct`` (percent; <=0 disables a\n single guard).\n ``direction_mode`` / ``allow_short`` / ``regime_override``: the direction\n controls from the create tools (deterministic signals -- DYOR).\n ``target_allocation``: new mint->weight basket (rebalance / vault /\n yield_farm).\n ``interval_seconds``: new tick interval, used from the next tick on.\n ``reason``: free text recorded on the strategy's audit log.\n\nREFUSED (returns ``immutable_config_key``): ``target_token`` /\n``source_token`` / ``tracked_wallet`` / ``venue`` / composite\n``definition``. These define WHAT the strategy trades -- editing them in\nplace would desync the executor's position bookkeeping or strand an open\nperp leg on the venue it was opened against. Cancel and create a new\nstrategy for those. A STOPPED strategy is final and cannot be modified;\na paused one can (the edit does not resume it -- use strategy_resume).\n\nThe merged config is dry-run through the strategy's executor before it is\npersisted, so an invalid edit is rejected (``invalid_config``) rather than\nlatching the live strategy into ``error`` on its next tick.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "config_updates": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "interval_seconds": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "default": null }, "reason": { "default": "", "type": "string" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "remove_keys": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "strategy_id": { "type": "integer" }, "target_allocation": { "anyOf": [ { "additionalProperties": { "type": "number" }, "type": "object" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "strategy_id", "wallet_address" ], "type": "object" }, "name": "strategy_modify", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a momentum strategy -- fast/slow SMA crossover entry/exit.\n\nBuys on a bullish cross (fast SMA > slow SMA), sells on a bearish cross.\nDISCRETIONARY (SEC framework): the model interprets a signal\nand converts it to a trade, so targeting a tokenized SECURITY forces\nper-execution user confirmation before the scheduled dispatcher will run a\ntick (``strategies.tasks.execute_strategy`` requires ``user_confirmed=True``;\ncrypto targets stay fully autonomous). Call asset_classification first.\n\n``risk`` / direction params: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "fast": { "default": 5, "type": "integer" }, "interval_seconds": { "default": 3600, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "slow": { "default": 20, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "target_token": { "type": "string" }, "usd_per_buy": { "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_buy" ], "type": "object" }, "name": "strategy_momentum_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Manually pause a strategy (status=paused_manual; stops dispatch).", "inputSchema": { "additionalProperties": false, "properties": { "strategy_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "strategy_id", "wallet_address" ], "type": "object" }, "name": "strategy_pause", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a perp-grid strategy -- a ladder of perp LONGS accumulated on dips.\n\nRoutes through the multi-venue perps VENUE ADAPTER (hard rule 2; Jupiter\nPerps primary). Around a rolling center price (SMA, or an explicit\n``center_price``), each ``grid_spacing_pct`` move below center is one rung;\ncrossing a deeper rung opens a perp long sized ``usd_per_level`` at\n``leverage``. PAUSES new rungs in a trending (bull/bear) regime and closes\nthe ladder in a bear (stop the bleed); tightens spacing in range, widens\nwhen volatile. Only an asset with a mapped perp market (currently SOL) can\nopen -- see get_venue_status for routable markets. ``venue`` optional\n(defaults to the configured primary); a Tier B (custodied) venue needs\n``acknowledge_tier_b=true`` after reviewing its ``custody_disclosure``.\n\n``risk``: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "acknowledge_tier_b": { "default": false, "type": "boolean" }, "center_period": { "default": 20, "type": "integer" }, "center_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "grid_levels": { "default": 5, "type": "integer" }, "grid_spacing_pct": { "default": 0.02, "type": "number" }, "interval_seconds": { "default": 300, "type": "integer" }, "leverage": { "default": 1, "type": "number" }, "range_tighten": { "default": 0.5, "type": "number" }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "target_token": { "type": "string" }, "usd_per_level": { "type": "number" }, "venue": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "volatile_widen": { "default": 2, "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_level" ], "type": "object" }, "name": "strategy_perp_grid_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a downside-protection monitor on a held position.\n\nShares the stop-loss executor -- identical config/mechanics to\n``strategy_stoploss_create`` -- framed as a pure downside guard. At least\none of ``stop_loss_pct`` / ``take_profit_pct`` / ``trailing`` must be set.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "entry_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "interval_seconds": { "default": 60, "type": "integer" }, "position_amount": { "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "stop_loss_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "take_profit_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "target_token": { "type": "string" }, "trailing": { "default": false, "type": "boolean" }, "trailing_distance_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "position_amount" ], "type": "object" }, "name": "strategy_protect_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a portfolio-rebalance strategy toward ``target_allocation`` (mint->weight).\n\nDirection (optional, deterministic signal): ``direction_mode`` /\n``allow_short`` / ``regime_override`` -- see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "drift_threshold_pct": { "default": 5, "type": "number" }, "interval_seconds": { "default": 3600, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "target_allocation": { "additionalProperties": { "type": "number" }, "type": "object" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_allocation" ], "type": "object" }, "name": "strategy_rebalance_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Re-enable a paused strategy (manual re-enable after a drawdown pause).\n\nThe drawdown kill switch latches a strategy to\n``paused_drawdown`` and requires this explicit owner action to resume; the\nequity high-water mark is reset so it does not immediately re-trip.", "inputSchema": { "additionalProperties": false, "properties": { "strategy_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "strategy_id", "wallet_address" ], "type": "object" }, "name": "strategy_resume", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a sentiment strategy -- trades an aggregate sentiment score.\n\nBuys when the score is >= ``bull_threshold`` (flat), sells when it is\n<= ``bear_threshold`` (holding); the neutral band holds. The score is\nsourced live from market intelligence each tick, or pinned via\n``sentiment_score``. DISCRETIONARY (SEC framework): targeting\na tokenized SECURITY forces per-execution ``user_confirmed`` at execution\n(crypto stays fully autonomous). Call asset_classification first.\n\n``risk`` / direction params: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "bear_threshold": { "default": -0.15, "type": "number" }, "bull_threshold": { "default": 0.15, "type": "number" }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "interval_seconds": { "default": 3600, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "sentiment_score": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "target_token": { "type": "string" }, "usd_per_buy": { "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_buy" ], "type": "object" }, "name": "strategy_sentiment_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a snipe/scalping strategy -- dip-buy with a fast take-profit/stop exit.\n\nFlat: buys ``usd_per_buy`` when price is ``entry_dip_pct`` below the close\n``lookback`` ticks ago. Holding: exits on a tight ``take_profit_pct`` OR\n``stop_loss_pct`` -- many small round-trips. Runs on a short interval\n(default 60s) since it reads a per-tick rolling price window that must\naccumulate ``lookback`` + 1 observations before it can enter.\n\n``risk`` / direction params: see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "entry_dip_pct": { "default": 0.005, "type": "number" }, "interval_seconds": { "default": 60, "type": "integer" }, "lookback": { "default": 3, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "stop_loss_pct": { "default": 0.005, "type": "number" }, "take_profit_pct": { "default": 0.01, "type": "number" }, "target_token": { "type": "string" }, "usd_per_buy": { "type": "number" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "usd_per_buy" ], "type": "object" }, "name": "strategy_snipe_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Status + last execution of one strategy (scoped to the caller's wallet).", "inputSchema": { "additionalProperties": false, "properties": { "strategy_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "strategy_id", "wallet_address" ], "type": "object" }, "name": "strategy_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a stop-loss / take-profit / trailing-stop monitor on a held position.\n\n``position_amount`` is base units of ``target_token`` to liquidate on\ntrigger. At least one of ``stop_loss_pct`` / ``take_profit_pct`` / a trailing\nconfig should be set (fractions, e.g. 0.15 == 15%).\n\nDirection (optional, deterministic signal): ``direction_mode`` /\n``allow_short`` / ``regime_override`` -- see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "entry_price": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "interval_seconds": { "default": 60, "type": "integer" }, "position_amount": { "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "source_token": { "default": "USDC", "type": "string" }, "stop_loss_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "take_profit_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "target_token": { "type": "string" }, "trailing": { "default": false, "type": "boolean" }, "trailing_distance_pct": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "default": null }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_token", "position_amount" ], "type": "object" }, "name": "strategy_stoploss_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a vault strategy -- a target-allocation basket held via rebalancing.\n\nShares the rebalance executor -- identical config/mechanics to\n``strategy_rebalance_create`` (``target_allocation`` mint->weight,\n``drift_threshold_pct``) -- framed as a passive basket rather than an active\nrebalance loop. No external vault/LP deposit (hard rule 1): the\nnon-custodial swap pipeline only rotates spot holdings toward the target\nweights.\n\nDirection (optional, deterministic signal): ``direction_mode`` /\n``allow_short`` / ``regime_override`` -- see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "drift_threshold_pct": { "default": 5, "type": "number" }, "interval_seconds": { "default": 3600, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "target_allocation": { "additionalProperties": { "type": "number" }, "type": "object" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_allocation" ], "type": "object" }, "name": "strategy_vault_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Create a yield-farm strategy -- maintains a target basket allocation.\n\nShares the rebalance executor (config identical to\n``strategy_rebalance_create``): depositing into an external yield protocol\n/ LP position has no faithful swap-pipeline analogue, so this models a\nyield farm as keeping a target allocation across the basket via converging\nrebalance swaps (hard rule 1: the non-custodial pipeline only rotates spot\nholdings, never deposits externally).\n\nDirection (optional, deterministic signal): ``direction_mode`` /\n``allow_short`` / ``regime_override`` -- see ``strategy_dca_create``.", "inputSchema": { "additionalProperties": false, "properties": { "allow_short": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": null }, "direction_mode": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "drift_threshold_pct": { "default": 5, "type": "number" }, "interval_seconds": { "default": 3600, "type": "integer" }, "regime_override": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "risk": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "target_allocation": { "additionalProperties": { "type": "number" }, "type": "object" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "target_allocation" ], "type": "object" }, "name": "strategy_yield_farm_create", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Submit the OWNER-SIGNED ``register_identity`` transaction and complete the binding.\n\nSubmits the transaction, then VERIFIES on chain before stamping anything:\nthe account at ``identity_pda`` must be OWNED by the AGNTA agent-registry\nprogram, carry the AgentIdentity discriminator, AND carry this wallet's own\nauthority pubkey. Only then does the wallet move ``pending`` ->\n``registered``. A signature string is never treated as proof, and an agent\ncan never self-assert its own binding. A duplicate submit is not an error\n-- the on-chain check decides; when the account is not yet visible the\nwallet stays ``pending`` and the caller polls\npoll_agnta_identity_registration.\n\nNon-custodial (hard rule 1): ``signed_transaction_base64`` is the owner's\nPUBLIC signed artefact -- Crank never sees, stores or logs a key or seed.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "identity_pda": { "type": "string" }, "signed_transaction_base64": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "identity_pda", "signed_transaction_base64" ], "type": "object" }, "name": "submit_agnta_identity_registration", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Historical parameter observations for one of YOUR strategies (free read).\n\nCompares the strategy's realised outcomes against your other strategies\nof the same type that ran different parameter values, and returns the\nobserved differences ranked by realised P&L -- historical performance\ndata only, never advice, and nothing is changed by this call (PROPOSE\nflow: acting on an observation is your call via the strategy tools,\nwhere every policy/risk gate still applies).\n\nWorkflow: ORIENT -> DECIDE step -- review observations, then adjust via\nstrategy tools if YOU decide to.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "strategy_id": { "type": "integer" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "strategy_id" ], "type": "object" }, "name": "suggest_parameter_adjustment", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Token metadata, price, liquidity, volume, holder count.\n\nProvide token_address (mint) or a known symbol. Merges Helius (metadata)\nwith Birdeye (market data).\n\nFree (no technology service fee) -- a read with no transaction notional.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "symbol": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "token_address": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null } }, "type": "object" }, "name": "token_info", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Spot-trade a tokenized equity (xStocks / Ondo) via Jupiter, non-custodial.\n\nside: buy | sell. amount is in base units of the INPUT token (USDC 6dp for a\nbuy, the equity token for a sell). These are tokenized SECURITIES: the call\nis geo-gated (Reg S = no US persons; declare jurisdiction once via the\njurisdiction arg) and OFAC-screened, and requires per-execution confirmation\n-- WITHOUT confirm=true it returns a quote + disclaimer and does NOT execute\n(no autonomous equity execution). With confirm=true it returns an UNSIGNED\nbase64 tx to sign + broadcast; pass signed_transaction to broadcast a\ncaller-signed tx. Value-bearing: past the daily free tier an x402\npayment_header is required. ip = caller origin IP for the Reg S geo gate\n(US IP -> refused even with an attestation; an agent's Railway Singapore\negress resolves to SG and passes). ``venue_hint`` is ADVISORY, never required -- equity routes via the issuer\nregistry (one surface today); an unknown hint raises.\n\n``idempotency_key`` (optional): see jupiter_swap -- same\nreplay-on-retry semantics, same key reused across build + broadcast.\n\n``verify`` (extending default True): when\nbroadcasting (signed_transaction supplied), await on-chain confirmation\nand re-read the equity mint balance -- the response gains a\n``verification`` block ({confirmed, slot, post_state,\nexpected_vs_actual}). Gate follow-on decisions on\n``verification.confirmed``, never on tx_signature alone. Set False to\nskip for latency-sensitive callers. Verify any prior signature later\nwith the standalone ``verify_transaction`` tool.", "inputSchema": { "additionalProperties": false, "properties": { "allow_unverified": { "default": false, "type": "boolean" }, "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "confirm": { "default": false, "type": "boolean" }, "idempotency_key": { "default": "", "type": "string" }, "ip": { "default": "", "type": "string" }, "jurisdiction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "side": { "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "slippage_bps": { "default": 50, "type": "integer" }, "symbol": { "type": "string" }, "venue_hint": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "symbol", "side", "amount", "wallet_address" ], "type": "object" }, "name": "trade_equity", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Withdraw a published journal card (free write).\n\nPublishing a decision with share_journal_card is an explicit act by\nthe owner; this is the equally explicit act of taking it back. After\nthis call, the public card at its card_url and the OG-image asset\nboth 404 immediately -- the row is private again, exactly as it was\nbefore the first publish.\n\nWallet-scoped like every other Layer 1 tool: you can only unpublish a\ndecision your own wallet owns. Calling this on a decision that is\nalready private (or was never published) is a safe no-op, not an\nerror -- ``unpublished`` in the response tells you whether a\nwithdrawal actually happened.\n\nThe cached OG image, if one was generated, is left on disk (not\ndeleted) -- the public routes gate on publication state, not file\npresence, so the takedown is immediate either way, and a later\nre-publish of the same decision reuses the image instead of paying to\nregenerate it.\n\nWorkflow: the symmetric undo of share_journal_card.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "decision_id": { "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "decision_id" ], "type": "object" }, "name": "unpublish_journal_card", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Unstake an LST back to SOL (non-custodial).\n\nlst_token is a mint (mSOL/jitoSOL/bSOL); amount in base units. mSOL routes\nvia Marinade, others via the Sanctum router. Returns an UNSIGNED base64 tx.\nThe technology service fee is charged on the unstaked-LST notional past the\ndaily free tier (x402 payment_header).\n\n``idempotency_key`` (optional): a client-generated UUID.\nRetrying with the same key + same args replays the original result instead\nof re-unstaking. Reuse the SAME key across the build call and its\n``signed_transaction`` completion call -- see liquid_stake;\nthe two legs dedupe independently, so this never raises\nIDEMPOTENCY_CONFLICT.\n\n``signed_transaction`` / ``verify`` (two-phase execution):\nsee liquid_stake -- re-call with the signed tx and Crank broadcasts it,\nconfirms it on-chain, and re-reads the LST + SOL balances.", "inputSchema": { "additionalProperties": false, "properties": { "amount": { "type": "integer" }, "caller_id": { "default": "", "type": "string" }, "idempotency_key": { "default": "", "type": "string" }, "lst_token": { "type": "string" }, "pay_in_crank": { "default": false, "type": "boolean" }, "payment_header": { "default": "", "type": "string" }, "signed_transaction": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "verify": { "default": true, "type": "boolean" }, "wallet_address": { "type": "string" } }, "required": [ "lst_token", "amount", "wallet_address" ], "type": "object" }, "name": "unstake_lst", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Patch an agent profile's metadata (display_name, capabilities, endpoints).\n\nmetadata is a dict of writable fields; capabilities are validated if present.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "metadata": { "additionalProperties": true, "type": "object" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address", "metadata" ], "type": "object" }, "name": "update_agent_profile", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Side-by-side risk comparison of two venues for a routing decision.\n\nRead-only. Returns each venue's full risk record, the safer venue, and the\ncomposite-score delta. e.g. compare \"jupiter\" vs \"pacifica\" before routing.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "venue_a": { "type": "string" }, "venue_b": { "type": "string" } }, "required": [ "venue_a", "venue_b" ], "type": "object" }, "name": "venue_risk_comparison", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Multi-layer authenticity check for a token mint (read-only, no execution).\n\nRuns the same five-layer verification the swap/trade tools enforce before\nbuilding a transaction: registry allow-list, Jupiter verified list, Metaplex\nmetadata authority, minimum liquidity, and token age + holder count. Returns\nverification_status (verified | unverified | suspicious | blocked), the\nreasons, non-blocking warnings, and the per-layer findings. Call this before\nswapping into an unfamiliar token.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "symbol": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "token_address": { "type": "string" } }, "required": [ "token_address" ], "type": "object" }, "name": "verify_token", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Verify any prior transaction signature on demand (FREE read).\n\nPost-trade verification (harness spec R13): awaits\non-chain confirmation of ``tx_signature`` at ``commitment`` level (up to\n``timeout_s``) and, when a state hint is supplied, re-reads the relevant\nstate to compare against what was expected:\n\n - ``mint`` (+ ``wallet_address``): re-reads that SPL/SOL token balance.\n - ``market`` (+ ``wallet_address``): re-reads the Drift perp position.\n - ``protocol`` (+ ``wallet_address``, optional ``market`` /\n ``marginfi_account``): re-reads the lending obligation health.\n\nReturns ``{confirmed, slot, commitment, post_state, expected_vs_actual,\nretry_guidance}``. ``confirmed`` is False (never True) on a timeout --\nNEVER treat an unconfirmed/timed-out result as success; ``retry_guidance``\nnames the next step. Use this after signing + broadcasting a transaction\nyourself (place_perp_order, lend_deposit/borrow/repay, and every other\nunsigned-tx tool never broadcast server-side) to confirm it actually\nlanded before treating the position/balance as changed.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "commitment": { "default": "confirmed", "type": "string" }, "marginfi_account": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "market": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "mint": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "protocol": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null }, "timeout_s": { "default": 30, "type": "number" }, "tx_signature": { "type": "string" }, "wallet_address": { "default": "", "type": "string" } }, "required": [ "tx_signature" ], "type": "object" }, "name": "verify_transaction", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "On-chain proof the treasury actually received settled x402 USDC.\n\nWires ``services.x402_settlement.verify_treasury_settlement`` (\nreal on-chain proof: treasury USDC ATA balance read as the primary signal,\nplus settle-tx signature confirmation) up to an MCP tool -- the follow-up\nto which intentionally split the on-chain proof\nlogic from this wiring to avoid file collisions across parallel sessions.\n\n``signatures`` is optional: when omitted, this tool pulls recent settled\n``X402PaymentRecord.tx_signature`` values itself (via\n``django_bridge.recent_x402_signatures``, same window shape as\n``reconcile_x402_settlement``) over the last ``since_iso`` window (or all\ntime), capped at ``signature_limit`` to bound RPC round trips -- so a\ncaller does not have to hand-assemble signatures to get a real proof.\nPass an explicit ``signatures`` list to check specific settle-tx hashes\ninstead (bypasses the DB lookup entirely).\n\n``verified`` is True only when every checked signature confirms on-chain\nAND (if ``expected_usd`` is given) the treasury balance covers it -- see\nthe service docstring for the full non-falsely-asserting contract. Raises\nCONFIG_ERROR if no treasury wallet is configured, UPSTREAM_ERROR\n(retryable) on an RPC failure -- never a silent ``verified=False``.\n\nFREE read (never gated, never in x402 PAID_TOOLS): public addresses/\nsignatures/balances only, never a key (hard rule 1).", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "expected_usd": { "default": "", "type": "string" }, "signature_limit": { "default": 25, "type": "integer" }, "signatures": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "default": null }, "since_iso": { "default": "", "type": "string" } }, "type": "object" }, "name": "verify_treasury_settlement_status", "outputSchema": { "additionalProperties": true, "type": "object" } }, { "description": "Current state, policy summary, recent activity, total volume, and tier.", "inputSchema": { "additionalProperties": false, "properties": { "caller_id": { "default": "", "type": "string" }, "wallet_address": { "type": "string" } }, "required": [ "wallet_address" ], "type": "object" }, "name": "wallet_status", "outputSchema": { "additionalProperties": true, "type": "object" } } ] }
Verify it yourselfcurl -s https://api.teppi.xyz/v1/evidence/sha256:c1375d95eefaabea09df7d73514723d71d3b1d440dbeaa68934478fb7b3020c1 | sha256sum