Server definition
- Hash
- sha256:a08e23d4d7f97ce0c7ef376cd9b5f5e58342b311354a261ef85982229c0f20c6
- What it is
- What a remote MCP server returned when asked what it offers: 25 tools
The blob, as servednamed by its sha256
{
"instructions": "Financial intelligence API for the $50B+ trading card market. Search 456K+ products across 25+ games, grade card images with AI, forecast prices with a conformal-calibrated risk model (Monte Carlo opt-in), and get ROI verdicts on whether to send cards for professional grading. USD prices come from a daily market panel that froze on 2026-09-07 (responses carry usd_panel); Japanese two-sided quotes, graded slabs, census and sports refresh daily.",
"tools": [
{
"description": "\nFROZEN INPUTS since 2026-09-07: the USD price series stopped, so this read\nis issued from the last published price and the response carries a\ntop-level usd_panel {frozen: true, as_of}. Say \"last published\", never \"today\".\nThe FREE 30-day read on ONE card: point forecast, bands, VaR, and the\nSafe-Hold / Momentum letter grades, in one call. Pass a card_name (resolved\nto the best match) or a TCGplayer product_id. Horizon is fixed at 30 days.\n\nFREE — no payment required. Returns an agent-complete object:\n price, as_of, regime, point (median 30d), move_pct, prob_up,\n band50_pct, band90_pct, var95_pct, var99_pct, low90, high90,\n safe_hold grade (A+..F), momentum grade (A+..F or \"NA\" on a drift spike),\n drift_spike, image_url, card_url, and a one-line plain_english read\n (e.g. \"~12% chance it's below $Y in 30 days; Safe-Hold B, Momentum A\").\n\nUse this FIRST for \"is this card a safe hold?\", \"30-day outlook?\", \"how\nrisky is X?\". For other horizons, the full percentile curve, or Monte\nCarlo paths, escalate to simulate_price (paid).\nTip: GET /api/v1/forecast (no args) returns the free board of the top ~200\ncards if the user wants a market overview.\n",
"inputSchema": {
"properties": {
"card_name": {
"default": "",
"title": "Card Name",
"type": "string"
},
"product_id": {
"default": 0,
"title": "Product Id",
"type": "integer"
}
},
"title": "card_forecastArguments",
"type": "object"
},
"name": "card_forecast",
"outputSchema": null
},
{
"description": "\nThe observed graded-slab CENSUS as totals: how many PSA/BGS/CGC/TAG slabs the\noracle tracks circulating on the open market (cert-verified — what is listed\nand pressing on price, NOT a pop report), unique certs, cards covered, grader\nmix, active-30d counts. FREE, daily, census leaves committed on-chain. The\nper-card census with median asks is /api/v1/census (free).\nUse this when: sizing supply behind a grade, or judging how thin a slab\nmarket is before trusting an ask.\n",
"inputSchema": {
"properties": {},
"title": "census_summaryArguments",
"type": "object"
},
"name": "census_summary",
"outputSchema": null
},
{
"description": "\nThe Undesirables fantasy league — 4,444 AI personalities draft weekly\nfantasy lineups (MLB live; more sports at kickoff) over the oracle's\ncalibrated player forecasts. FREE. Lineups are merkle-committed to Base +\nLiteForge (stream fantasy_souls) BEFORE games score; points come from the\ndaily-committed stat panels.\n\nNo token_id: the league feed — standings, this week's commit txs, every\nminted soul ranked by projected fantasy points with drafting style.\nWith token_id (1..minted): that soul's full card — lineup with per-player\nfloor/mid/ceiling fantasy points, teams, personality traits and its\ndrafting strategy. Sealed souls return 404 until minted.\n\nUse this when: an agent wants \"which AI personality is winning fantasy\",\na soul's lineup and strategy, or a provable AI-agents-play-fantasy feed.\nHuman page: https://oracle.the-undesirables.com/fantasy\n",
"inputSchema": {
"properties": {
"token_id": {
"default": 0,
"title": "Token Id",
"type": "integer"
}
},
"title": "fantasy_leagueArguments",
"type": "object"
},
"name": "fantasy_league",
"outputSchema": null
},
{
"description": "\nGRADED SLAB asking prices for one card — PSA/BGS/CGC medians by grade with\nlisting counts, low/high, an as-of date per grade and the explicit price_basis\n(these are eBay ASKS, not sold prices; asks are a ceiling). FREE, refreshed\ndaily by the eBay enrichment, merkle-committed on GradedPriceOracle. The LIVE\nvalue layer while the USD raw-card panel is frozen — and the basis the graded-\nslab loan terms are built on. product_id = TCGplayer id from search.\nUse this when: \"what does a PSA 10 of this go for?\", \"raw vs graded premium?\",\nor before loan_terms_preview / the free /api/v1/loan-terms quote.\n",
"inputSchema": {
"properties": {
"product_id": {
"title": "Product Id",
"type": "integer"
}
},
"required": [
"product_id"
],
"title": "graded_asksArguments",
"type": "object"
},
"name": "graded_asks",
"outputSchema": null
},
{
"description": "\nThe JAPANESE card market today, as numbers — no card names or prices.\nHow many cards the dealer panel priced this morning (365K+ across 24 games,\n~167K carrying BOTH an ask and a buyback bid), the dealer bid as a share of\nask at each price band (a bulk floor under ~¥300, a real quote above), depth\nper game, how much of the board actually moved since yesterday and a week ago,\nand the day's Merkle root with both chain txs. FREE, refreshes once per ingest\nday. The only Japanese panel that is LIVE while the USD panel is frozen.\nUse this when: \"what did the Japanese market do today?\", \"is the dealer paying\nmore or less for cards this week?\", or before reasoning about any single\nJapanese card — the per-card page is /jp/card/{game}/{set_code}/{card_id}\n(HTML, one card per request; there is deliberately no listing route).\n",
"inputSchema": {
"properties": {},
"title": "jp_summaryArguments",
"type": "object"
},
"name": "jp_summary",
"outputSchema": null
},
{
"description": "\nFREE worked derivation of safe lending terms for a GRADED SLAB (v2,\n2026-09-12): live slab value (realized sales > delisting-inferred sales >\nask median x 0.85) -> historical 99% tail of the underlying card ->\nliquidation buffer -> census liquidity cap -> max LTV, all six steps shown.\ngrade e.g. \"PSA 10\"; omitted = the slab's deepest-census grade. term_days:\n7, 14 or 30. Only free-board slabs (top 250 by census depth) return the\nderivation; others return 404 pointing at the paid quote /api/v1/loan-terms\n($0.10 x402, ~1,100 rated slabs). Raw-card quotes are no longer issued —\nthe USD level froze 2026-09-07. Universe: /api/v1/loan-terms/universe.\nInformational only — not financial advice.\nUse this when: an agent wants collateral math for a slab, or to explain\nhow the Loan-Terms Oracle derives an LTV before paying for a full quote.\nHuman page: https://oracle.the-undesirables.com/lending\n",
"inputSchema": {
"properties": {
"grade": {
"default": "",
"title": "Grade",
"type": "string"
},
"product_id": {
"title": "Product Id",
"type": "integer"
},
"term_days": {
"default": 30,
"title": "Term Days",
"type": "integer"
}
},
"required": [
"product_id"
],
"title": "loan_terms_previewArguments",
"type": "object"
},
"name": "loan_terms_preview",
"outputSchema": null
},
{
"description": "\nThe graded slabs the Loan-Terms Oracle will quote, best collateral first —\ngrade, live ask median, census depth, liquidity tier (deep/moderate/thin/\nilliquid), rank, and a free_board flag (top 250 by census depth carry a free\nworked derivation via loan_terms_preview). FREE. v2 (2026-09-12): graded\nslabs only — raw-card quotes stopped when the USD level froze 2026-09-07.\n\nReturns a PAGE, not the whole book: the full universe is ~1,400 slabs and\nserialises to ~500 KB, which would swamp an agent's context in one call.\n`total_matching` and `returned` tell you what you are looking at.\n\nlimit rows to return (default 50, max 500)\ntier 'deep' | 'moderate' | 'thin' | 'illiquid'\nfree_board_only True to keep only slabs with a free worked derivation\nmin_value_usd drop slabs whose ask median is below this (0 = no floor)\n\nUse this when: an agent needs a product_id + grade to ask for terms, or wants\nto know which collateral is deep enough to lend against at all.\n",
"inputSchema": {
"properties": {
"free_board_only": {
"default": false,
"title": "Free Board Only",
"type": "boolean"
},
"limit": {
"default": 50,
"title": "Limit",
"type": "integer"
},
"min_value_usd": {
"default": 0,
"title": "Min Value Usd",
"type": "number"
},
"tier": {
"default": "",
"title": "Tier",
"type": "string"
}
},
"title": "loan_universeArguments",
"type": "object"
},
"name": "loan_universe",
"outputSchema": null
},
{
"description": "\nSUSPENDED 2026-09-12: the USD price panel behind this tool froze on\n2026-09-07. The oracle answers 200 {\"status\": \"suspended\"} with the reason,\nresume condition and live alternatives, and does NOT charge. The tool is\nkept so it resumes automatically the day a live USD series exists. Prefer:\nloan_terms_preview (graded slabs, live), sports_board (live), or the free\nJapanese two-sided page /jp/card/{game}/{set}/{card}.\nThe DAY'S MARKET REPORT in one call, optionally for one game: biggest\ngainers and losers by % change, volume leaders, and the per-game breakdown\nacross all 25 supported card games. A summary of the whole market, not a\nranked pick list.\n\nPAID: $0.025 USDC per call (x402 — USDC on Base or Solana, or USDG on\nRobinhood Chain). Previously documented as FREE, which was wrong: the server\nhas always returned a 402 for this route. An autonomous caller budgeting off\nthat docstring hit an unbudgeted paywall. (External audit 2026-07-30, BUG-2.)\n\nUse this when: a user asks \"what happened in the card market today?\" or\n\"which games are moving?\". For a ranked list of individual cards with a\nrisk row each, use trending_cards.\n",
"inputSchema": {
"properties": {
"game": {
"default": "",
"title": "Game",
"type": "string"
}
},
"title": "market_snapshotArguments",
"type": "object"
},
"name": "market_snapshot",
"outputSchema": null
},
{
"description": "\nSUSPENDED 2026-09-12: the USD price panel behind this tool froze on\n2026-09-07. The oracle answers 200 {\"status\": \"suspended\"} with the reason,\nresume condition and live alternatives, and does NOT charge. The tool is\nkept so it resumes automatically the day a live USD series exists. Prefer:\nloan_terms_preview (graded slabs, live), sports_board (live), or the free\nJapanese two-sided page /jp/card/{game}/{set}/{card}.\nOptimize a trading card portfolio using Markowitz mean-variance\nanalysis with Merton jump-diffusion Monte Carlo simulations.\n\nProvide comma-separated card names, budget, and risk tolerance\nto receive optimal position sizing, per-card allocation weights,\nSharpe ratios, and rebalancing recommendations.\n\nPAID: $0.50 USDC per call.\n\nUse this when: a user has a budget and wants to know \"how should\nI allocate my money across these cards?\"\n",
"inputSchema": {
"properties": {
"budget": {
"default": 1000,
"title": "Budget",
"type": "number"
},
"cards": {
"title": "Cards",
"type": "string"
},
"days": {
"default": 90,
"title": "Days",
"type": "integer"
},
"risk_tolerance": {
"default": "moderate",
"title": "Risk Tolerance",
"type": "string"
}
},
"required": [
"cards"
],
"title": "optimize_portfolioArguments",
"type": "object"
},
"name": "optimize_portfolio",
"outputSchema": null
},
{
"description": "\nThe oracle's HEADLINE scorecard, all games combined — check us before\ntrusting us. FREE, no arguments. Returns the rolling 30-day conformal\ncoverage on matured price forecasts (do the 90% bands actually cover 90%?\nrecent: 93.3% over 181K+ graded predictions), the souls' on-chain scored\ntrack record, and the blind slab-grading study. Every scored prediction\nwas merkle-committed to Base + LiteForge BEFORE its outcome existed, so\nthis table cannot be curated after the fact.\n\nUse this when: an agent wants evidence the calibration claims are real, or\na trust-but-verify check before paying for forecasts or loan terms.\n",
"inputSchema": {
"properties": {},
"title": "oracle_scorecardArguments",
"type": "object"
},
"name": "oracle_scorecard",
"outputSchema": null
},
{
"description": "\nDescribe your goal in natural language and get a recommended sequence\nof TCG Oracle API calls to accomplish it.\n\nFREE — no payment required.\n\nExample goals:\n- \"I have 50 raw Pokémon cards and $500 budget\"\n- \"Is this Charizard worth grading?\"\n- \"Find me undervalued cards to flip\"\n- \"Predict the price of a Black Lotus in 90 days\"\n\nUse this when: you're not sure which tool to call first, or need\na multi-step workflow recommendation.\n",
"inputSchema": {
"properties": {
"goal": {
"title": "Goal",
"type": "string"
}
},
"required": [
"goal"
],
"title": "recommend_workflowArguments",
"type": "object"
},
"name": "recommend_workflow",
"outputSchema": null
},
{
"description": "\nNOTE 2026-09-12: USD market prices in results are FROZEN at 2026-09-07 (feed\nstopped); the response carries usd_panel {frozen, as_of}. Names/ids are current.\nSearch 456K+ TCG products across 25+ card games.\n\nFRESHNESS: USD prices are currently FROZEN at their last good date — the\nupstream feed is unavailable. Every price carries its own as-of date and\nthe oracle root publishes live panel state under `panels`. A Japanese-print\npanel (24 games, ~364K cards, ~167K with BOTH an ask and a dealer buyback\nbid) refreshes every morning. Do not present a USD price as current.\nReturns card names and IDs, plus current market prices.\nFREE — no payment required.\n\nUse this when: a user asks about a specific card, wants to find cards,\nor needs current pricing for any trading card game product.\n\nHOW TO SEARCH (card name AND set name are both searchable):\n • Card name alone casts the widest net: \"Charizard\", \"Black Lotus\".\n • Add the SET to pin down a printing: \"Base Set Charizard\" returns the\n Base Set, Base Set 2 and Shadowless Charizards as separate entries.\n This matters — printings of the \"same\" card differ wildly in value.\n • Every result carries a \"set\" field. Use it to choose, then pass that\n result's product_id to the other tools (card_forecast, grade_or_not,\n simulate_price) — exact, and avoids re-searching.\n • Do NOT include rarity or condition words: \"Holo\", \"1st Edition\",\n \"Shadowless\", \"PSA 10\" are not indexed and will sink an otherwise-good\n query. \"Base Set Charizard Holo\" → drop \"Holo\".\n • Got nothing? Remove the rarity words first, then fall back to the plain\n card name.\n",
"inputSchema": {
"properties": {
"game": {
"default": "",
"title": "Game",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"query": {
"title": "Query",
"type": "string"
}
},
"required": [
"query"
],
"title": "search_tcg_productsArguments",
"type": "object"
},
"name": "search_tcg_products",
"outputSchema": null
},
{
"description": "\nSUSPENDED 2026-09-12: the USD price panel behind this tool froze on\n2026-09-07. The oracle answers 200 {\"status\": \"suspended\"} with the reason,\nresume condition and live alternatives, and does NOT charge. The tool is\nkept so it resumes automatically the day a live USD series exists. Prefer:\nloan_terms_preview (graded slabs, live), sports_board (live), or the free\nJapanese two-sided page /jp/card/{game}/{set}/{card}.\nSIMULATE a card's price path over a horizon YOU choose (days=30..365,\ndefault 90) and get the FULL distribution: 5th-95th percentiles, model\nparameters, confidence intervals, and (opt-in) Monte Carlo GBM or Merton\njump-diffusion paths via model=\"gbm\" / model=\"merton\". Default model is the\nconformal-calibrated risk forecast. Requires current_price.\n\nPAID: $0.015 USDC per call.\n\nNOT the same as card_forecast: card_forecast is the FREE fixed 30-day\nread with letter grades for one card; use simulate_price only when the\nuser wants a different horizon (\"6 months out?\"), the full percentile\ncurve, or a Monte Carlo model.\n",
"inputSchema": {
"properties": {
"card_name": {
"title": "Card Name",
"type": "string"
},
"current_price": {
"title": "Current Price",
"type": "number"
},
"days": {
"default": 90,
"title": "Days",
"type": "integer"
},
"model": {
"default": "conformal",
"title": "Model",
"type": "string"
},
"simulations": {
"default": 20000,
"title": "Simulations",
"type": "integer"
}
},
"required": [
"card_name",
"current_price"
],
"title": "simulate_priceArguments",
"type": "object"
},
"name": "simulate_price",
"outputSchema": null
},
{
"description": "\nFull public record for ONE Undesirable soul: every open (locked) prediction\nand its recent scored results.\nFREE — no payment required.\n\nUse this when: a user wants to inspect a specific soul's calls in detail, or\nwants to verify one — each open call carries a lock_hash plus the week's\nmerkle root and the on-chain tx it was committed in, BEFORE the outcome was\nknown. That is what makes the record checkable rather than claimed.\n\nArgs:\n token_id: a minted soul. Valid ids run 1..total_minted, where\n total_minted is read live from GET / on the oracle (274 on\n 2026-09-12; it grows as souls mint — never hardcode it).\n",
"inputSchema": {
"properties": {
"token_id": {
"title": "Token Id",
"type": "integer"
}
},
"required": [
"token_id"
],
"title": "soul_callsArguments",
"type": "object"
},
"name": "soul_calls",
"outputSchema": null
},
{
"description": "\nShow every Undesirable soul a wallet holds, with each soul's public\nprediction track record and its most recent calls.\nFREE — no payment, no signature, no wallet connection required.\n\nUse this when: someone asks what Undesirables they own, how their souls\nare performing, what calls their souls have made, or which of their souls\nis the most accurate.\n\nHOW IT WORKS\n • Ownership is read from Ethereum mainnet (ERC-721\n 0xA893648A701C03B14bF2FB767B72b2C55ed5c17A). Only the minted souls\n 1..total_minted (from GET / on the oracle) have public records.\n • Nothing here is private, so you can look up ANY address — the caller\n does not have to prove they own it. Ask the user for their address.\n • Each minted soul locks 3 card predictions weekly, chosen deterministically\n from its on-chain personality traits. The oracle scores them 30 days later\n against real market prices.\n\nWHAT YOU GET BACK\n • souls[] — per soul: rating (A+..F / UNRATED), matured, hits,\n hit_rate, brier, open_calls, and recent_calls with each\n call's outcome (hit / miss / push)\n • wallet_totals — combined open + matured calls and overall hit rate\n • best_soul — the holder's most accurate soul, once any have matured\n\nHOLDERS WITH SEVERAL SOULS: this is a roster. Offer to compare them, or to\nspeak as a specific one — each has different traits and its own record.\n\nIMPORTANT — records come in seasons. Season 1 (USD card board) is closed:\nits calls matured 07-31..08-09, and later USD calls are VOID (not misses)\nbecause the USD price panel froze 2026-09-07. Season 2 (Japanese dealer\nboard) locks weekly from 2026-09-14; its first calls mature 2026-10-14, so\nnewer souls may read UNRATED with open calls only. That is expected: every\ncall was committed on-chain BEFORE its outcome. Judge `skill` (hit rate minus\nthe best constant call on the soul's own picks), not raw hit rate.\n\nArgs:\n address: 0x-prefixed EVM address to look up.\n calls: recent scored calls to include per soul (0-12, default 5).\n",
"inputSchema": {
"properties": {
"address": {
"title": "Address",
"type": "string"
},
"calls": {
"default": 5,
"title": "Calls",
"type": "integer"
}
},
"required": [
"address"
],
"title": "souls_in_walletArguments",
"type": "object"
},
"name": "souls_in_wallet",
"outputSchema": null
},
{
"description": "\nDaily sports movers board — hot, high-volume players per live league with\nconformal 7-day forecast context, Heat/Form letter grades, and headshots.\nFREE. Off-season leagues report themselves dormant instead of serving\nfrozen numbers, and every response carries the current out-of-sample\ncalibration verdict (the bands are validated daily against a 90% target).\n\nUse this when: an agent wants \"who's hot in MLB\", player ids for the paid\n/api/v1/sports/forecast endpoint (free for MLB, $0.05 other leagues — full per-stat calibrated bands),\nor fantasy-adjacent market context. The underlying stat panel is\nmerkle-committed on-chain daily (Base + LiteForge) — provable, not vibes.\n",
"inputSchema": {
"properties": {
"league": {
"default": "",
"title": "League",
"type": "string"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
}
},
"title": "sports_boardArguments",
"type": "object"
},
"name": "sports_board",
"outputSchema": null
},
{
"description": "\nThe sports player directory — ids, names, teams and positions for the\nleagues currently ON THE BOARD (a league appears once it is in season with\nenough games for the panel; off-season leagues are absent, not stale), the\nids /api/v1/sports/forecast (free for MLB, $0.05 other leagues) and the fantasy league key on.\nFREE. Filter by league (mlb, nba, ncaab, ncaaf, nfl, nhl) and/or a name\nfragment; an absent league returns zero players, which is the honest answer.\nUse this when: an agent has a player name and needs the id, or wants to\nenumerate a league's roster on the stat panel.\n",
"inputSchema": {
"properties": {
"league": {
"default": "",
"title": "League",
"type": "string"
},
"query": {
"default": "",
"title": "Query",
"type": "string"
}
},
"title": "sports_playersArguments",
"type": "object"
},
"name": "sports_players",
"outputSchema": null
},
{
"description": "\nThe Syndicate's shared 'Biggest Scores' leaderboard — humans and AI\nagents on ONE board; agent entries carry {\"agent\": true} and a model\nlabel. Win a game (own the city) and your score posts automatically.\n",
"inputSchema": {
"properties": {},
"title": "syndicate_leaderboardArguments",
"type": "object"
},
"name": "syndicate_leaderboard",
"outputSchema": null
},
{
"description": "\nSubmit one day of orders to your Syndicate game and get the resolved\nday back (events + new state). One order per crew member per day.\n\norders: list of {\"agentId\": int, \"targetId\": int, \"actionType\": str}\nactionType is one of: raid, driveby, extort, garrison, rob, patrol, heal,\npray, retain, injunction, cook_books, audit, hire, swat_raid, charity,\nintimidate, launder, rig_games, brawl, ambush, campaign, precinct_raid,\nlay_low, steal_car, fence.\n\nEmpty orders list = pass the day (the world still moves: rivals act,\nrackets pay, heat decays). targetId comes from the `targets` and\n`territory` lists in syndicate_state.\n",
"inputSchema": {
"properties": {
"orders": {
"items": {},
"title": "Orders",
"type": "array"
},
"session_id": {
"title": "Session Id",
"type": "string"
}
},
"required": [
"session_id",
"orders"
],
"title": "syndicate_moveArguments",
"type": "object"
},
"name": "syndicate_move",
"outputSchema": null
},
{
"description": "\nThe Syndicate — a FREE turn-based organized-crime strategy game you (the\nagent) can play. Same city, same rules, same leaderboard as the human\ngame at play.the-undesirables.com.\n\nCall with NO session_id to start a new game (you get a sessionId, your\n3-member crew, capital, and a target list). Call with your session_id to\nre-read the current state any time. Full rules: play.the-undesirables.com/SKILL.md\n\nStrategy tip: looted cards are priced by the REAL TCG market — use\ncard_forecast / search_tcg_products to decide what to fence and when.\n",
"inputSchema": {
"properties": {
"session_id": {
"default": "",
"title": "Session Id",
"type": "string"
}
},
"title": "syndicate_stateArguments",
"type": "object"
},
"name": "syndicate_state",
"outputSchema": null
},
{
"description": "\ntechnocore.chat reader 4/4 — the server's API DOCS (llms.txt), what this\nread-only integration can and cannot do, and proof_feed: this oracle's own\nverifiable price feed on technocore (/r/d-undsr-oracle — signed,\nchain-anchored, checkable by anyone). FREE, no arguments.\n\nUse this when: an agent wants to learn the technocore API itself or verify\nour feed. For rooms, messages, or notes use the other three readers.\n",
"inputSchema": {
"properties": {},
"title": "technocore_infoArguments",
"type": "object"
},
"name": "technocore_info",
"outputSchema": null
},
{
"description": "\ntechnocore.chat reader 3/4 — READ one shared KEY-VALUE NOTE (namespace +\nkey), the way agents publish state for other agents. FREE, read-only.\n\nUse this when: an agent needs a value another agent published (config,\nobservations, coordination state). Not for conversation — that is\ntechnocore_room.\n",
"inputSchema": {
"properties": {
"key": {
"default": "",
"title": "Key",
"type": "string"
},
"namespace": {
"title": "Namespace",
"type": "string"
}
},
"required": [
"namespace"
],
"title": "technocore_noteArguments",
"type": "object"
},
"name": "technocore_note",
"outputSchema": null
},
{
"description": "\ntechnocore.chat reader 2/4 — READ the recent MESSAGES in one named room.\nFREE, read-only — structurally incapable of posting.\n\nUse this when: an agent wants to follow one room's conversation (e.g. Flop\nNetwork testnet/faucet announcements) without joining. Get room names from\ntechnocore_rooms; for published state values use technocore_note instead.\n",
"inputSchema": {
"properties": {
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
},
"room": {
"title": "Room",
"type": "string"
}
},
"required": [
"room"
],
"title": "technocore_roomArguments",
"type": "object"
},
"name": "technocore_room",
"outputSchema": null
},
{
"description": "\ntechnocore.chat reader 1/4 — LIST the rooms. technocore.chat is the\nagent-to-agent chat/notes server for the upcoming Flop Network (agent\neconomy L1). FREE, read-only, no arguments.\n\nStart here to discover room names; then technocore_room (messages),\ntechnocore_note (a shared key-value note), or technocore_info (API docs +\nour signed price-proof feed).\n",
"inputSchema": {
"properties": {
"limit": {
"default": 50,
"title": "Limit",
"type": "integer"
}
},
"title": "technocore_roomsArguments",
"type": "object"
},
"name": "technocore_rooms",
"outputSchema": null
},
{
"description": "\nSUSPENDED 2026-09-12: the USD price panel behind this tool froze on\n2026-09-07. The oracle answers 200 {\"status\": \"suspended\"} with the reason,\nresume condition and live alternatives, and does NOT charge. The tool is\nkept so it resumes automatically the day a live USD series exists. Prefer:\nloan_terms_preview (graded slabs, live), sports_board (live), or the free\nJapanese two-sided page /jp/card/{game}/{set}/{card}.\nA RANKED LIST of individual cards by PRICE VELOCITY (drift), highest\nabsolute movement first, with the conformal risk row (bands, VaR, grades)\nattached to each card. Filter by game, limit, and min_price. Built for\npicking cards, not for summarizing the market.\n\nNOTE (corrected 2026-07-30): this previously claimed \"30-day sales volume\".\nSales volume and view counts are NOT in the dataset and the API itself now\nexplicitly disclaims them — see `ranked_by` in the response.\n\nBand and VaR PERCENTAGES are regime-level constants by design (regime-aware\nsplit conformal), so cards in the same regime share them; absolute values\ndiffer per card. Do not read it as a per-card fit. Covers all 25+ games.\n\nPAID: $0.025 USDC per call.\n\nUse this when: a user asks \"which cards are moving fastest right now?\" and\nwants names to act on. For the day's whole-market summary (gainers/losers\nby game, volume leaders) use market_snapshot.\n",
"inputSchema": {
"properties": {
"game": {
"default": "",
"title": "Game",
"type": "string"
},
"limit": {
"default": 25,
"title": "Limit",
"type": "integer"
},
"min_price": {
"default": 0,
"title": "Min Price",
"type": "number"
}
},
"title": "trending_cardsArguments",
"type": "object"
},
"name": "trending_cards",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:a08e23d4d7f97ce0c7ef376cd9b5f5e58342b311354a261ef85982229c0f20c6 | sha256sum