Server definition
- Hash
- sha256:a7a728a6cede310a1f9024492c46acbeead088331a6a97b09103dc7b3a95bb9a
- What it is
- What a remote MCP server returned when asked what it offers: 15 tools
The blob, as servednamed by its sha256
{
"instructions": "Watch and manage an existing Gate project here. Obtain its project_id and authorized key from the setup endpoint, /mcp/setup. Use gate_list_apps to select an existing app and gate_list_approvers to check dedicated human approvers before gate_create_run; create apps and approval keys on the setup endpoint, /mcp/setup. Read held actions with gate_list_actions. Approving or rejecting a held action is done by a person with an approver key in the dashboard, by design. No MCP tool can approve actions. gate_read_audit shows recent calls, gate_export_audit_proof exports signed rows, and gate_verify_audit_proof checks an export. gate_get_run_tree shows delegation state; gate_get_run_timeline shows events. Review gate_learn_suggestions before gate_update_app applies them with explicit confirmation. /mcp retains the full compatibility catalog; old names remain callable here for the same capabilities.",
"tools": [
{
"description": "Gate Actions: give one agent session narrow, expiring permission. Actions are rules with {placeholders} bound by scope (e.g. \"PATCH /customers/{customer}/tickets/:id\" with scope {\"customer\":\"A\"}), each with an optional max and approval. Check gate_list_approvers for an active human approver before granting approval:true actions; create one on the setup endpoint, /mcp/setup if needed; without an active approver the grant is refused. Returns a run token (shown once) the agent sends as x-odile-run with its app key. Writes in a run need an Idempotency-Key. Give a write a check (\"GET /bookings?idempotency_key={key}\") and the agent can settle a lost answer with POST /g/<id>/_gate/recover.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"actions": {
"description": "Rules, or {rule, max, approval, check}",
"items": {
"anyOf": [
{
"type": "string"
},
{
"properties": {
"approval": {
"type": "boolean"
},
"check": {
"description": "For a write: the GET that finds it by key, e.g. \"GET /customers/{customer}/bookings?idempotency_key={key}\"; it must also be a GET action of the run",
"type": "string"
},
"idempotent": {
"description": "With check: the API dedupes on Idempotency-Key, so a not-found write may be retried",
"type": "boolean"
},
"max": {
"minimum": 1,
"type": "integer"
},
"rule": {
"type": "string"
}
},
"required": [
"rule"
],
"type": "object"
}
]
},
"maxItems": 50,
"minItems": 1,
"type": "array"
},
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"app": {
"description": "The app id (app_...) this run is for",
"type": "string"
},
"label": {
"description": "Optional: what the run is for, e.g. \"triage ticket 4411\"",
"type": "string"
},
"max_calls": {
"description": "Optional: calls allowed in the whole run",
"minimum": 1,
"type": "integer"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"scope": {
"additionalProperties": {
"type": "string"
},
"description": "Values for the {placeholders}, e.g. {\"customer\":\"A\"}",
"type": "object"
},
"ttl_seconds": {
"description": "How long the run lasts (default 3600)",
"maximum": 86400,
"minimum": 60,
"type": "integer"
}
},
"required": [
"project_id",
"admin_key",
"app",
"actions"
],
"type": "object"
},
"name": "gate_create_run",
"outputSchema": null
},
{
"description": "Hand a narrower run to another active app in the same project. Uses the parent app key and run token, never the admin key. Scope, expiry, approvals and ancestor budgets stay enforced; maximum depth five.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"actions": {
"items": {
"anyOf": [
{
"type": "string"
},
{
"properties": {
"approval": {
"type": "boolean"
},
"max": {
"minimum": 1,
"type": "integer"
},
"rule": {
"type": "string"
}
},
"required": [
"rule"
],
"type": "object"
}
]
},
"maxItems": 50,
"minItems": 1,
"type": "array"
},
"app": {
"description": "The destination app id",
"type": "string"
},
"app_key": {
"description": "The parent app key (gk_...)",
"type": "string"
},
"label": {
"description": "A short label for the delegated job",
"type": "string"
},
"max_calls": {
"maximum": 100000,
"minimum": 1,
"type": "integer"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"run_token": {
"description": "The parent run token (gr_...)",
"type": "string"
},
"ttl_seconds": {
"maximum": 86400,
"minimum": 60,
"type": "integer"
}
},
"required": [
"project_id",
"app_key",
"run_token",
"app",
"actions"
],
"type": "object"
},
"name": "gate_delegate_run",
"outputSchema": null
},
{
"description": "What a Gate refusal means and how to fix it, from the x-gate-refused header value (e.g. route_not_allowed).",
"inputSchema": {
"additionalProperties": false,
"properties": {
"reason": {
"description": "The x-gate-refused value",
"type": "string"
},
"recoverable": {
"description": "Whether the write was granted with a recovery check",
"type": "boolean"
}
},
"required": [
"reason"
],
"type": "object"
},
"name": "gate_explain_refusal",
"outputSchema": null
},
{
"description": "Which signed audit records can I export for verification? Returns chained audit rows, decided-action feature snapshots and signed anchors; use it for a portable tamper-evident export instead of gate_read_audit's recent-call view, then check it with gate_verify_audit_proof. No sealed paths/bodies, notes, keys or IPs in the action labels. Legacy actions lack snapshots and are excluded. store_audit=false has no chain. Follow next_from for audit rows and next_actions_after as actions_after for labels (10,000 each). Use API/SDK to verify exports above the MCP request size limit. The signature is HMAC-SHA256.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"actions_after": {
"description": "Action cursor from next_actions_after",
"type": "string"
},
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"from": {
"minimum": 1,
"type": "integer"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"to": {
"minimum": 1,
"type": "integer"
}
},
"required": [
"project_id",
"admin_key"
],
"type": "object"
},
"name": "gate_export_audit_proof",
"outputSchema": null
},
{
"description": "What are the project call trends and current usage? Returns project-wide 24-hour call aggregates, anomaly scores, idle apps and current-month usage; use it for operational trends rather than individual calls in gate_read_audit or one run in gate_get_run_timeline. Includes stored call counts by HTTP status and reason, measured duration through response headers (including upstream wait), per-app anomaly scores and 24-hour anomaly counts, idle apps (active apps whose key made no allowed call in the project's idle_days, default 14; a flag only, never a revoke), and separate current-month gateway usage: plan, used, allowed, plus upgrade URL and checkout path on Free at 80% or above. Only POST the checkout path when the admin asks to upgrade; reading metrics never starts checkout. Requires the project owner key or an active member key. Audit may be partial: invalid-key sampling and audit-off periods are disclosed. No upstream requests, quota use or policy changes; not a health certificate or performance guarantee. For individual calls use gate_read_audit.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
}
},
"required": [
"project_id",
"admin_key"
],
"type": "object"
},
"name": "gate_get_metrics",
"outputSchema": null
},
{
"description": "What happened during this run? Returns one run's call metadata, approvals and approver names, recovery outcomes and delegated children; use it to reconstruct that session instead of gate_read_audit's project-wide calls or gate_get_run_tree's permission state. No bodies or query values. One run only; the project-wide log is gate_read_audit.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"before": {
"description": "Older audit events (timeline pages have at most 500 events)",
"minimum": 1,
"type": "integer"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"run_id": {
"description": "The run id",
"type": "string"
}
},
"required": [
"project_id",
"admin_key",
"run_id"
],
"type": "object"
},
"name": "gate_get_run_timeline",
"outputSchema": null
},
{
"description": "Which permissions and delegated descendants does this run have? Returns one run and its delegated descendants without tokens; use it to inspect delegation and permission state instead of gate_get_run_timeline events. One run only; the project-wide log is gate_read_audit.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"run_id": {
"description": "The run id",
"type": "string"
}
},
"required": [
"project_id",
"admin_key",
"run_id"
],
"type": "object"
},
"name": "gate_get_run_tree",
"outputSchema": null
},
{
"description": "Read normalized routes and a suggested per-minute limit from an admin-enabled, time-boxed learning session. Records only method, normalized path templates and counts per minute; no query values, raw ids, headers or bodies. Never enables learning or applies rules.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"app": {
"description": "The app id",
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
}
},
"required": [
"project_id",
"admin_key",
"app"
],
"type": "object"
},
"name": "gate_learn_suggestions",
"outputSchema": null
},
{
"description": "Which actions are waiting for a human decision? Read held actions (pending by default, or another requested state) and their exact calls; this tool cannot decide or resubmit them. Approving or rejecting a held action is done by a person with an approver key in the dashboard, by design. No MCP tool can approve actions.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"state": {
"description": "Default: pending",
"enum": [
"pending",
"approved",
"rejected",
"executed",
"unknown",
"expired"
],
"type": "string"
}
},
"required": [
"project_id",
"admin_key"
],
"type": "object"
},
"name": "gate_list_actions",
"outputSchema": null
},
{
"description": "Approvers are people who decide held actions. List active and revoked dedicated approvers with ids, names and creation times; never returns keys or hashes. Team members with the approver role are a separate list. Requires the project owner key or an active member key. Create or revoke dedicated keys and inspect team roles on the setup endpoint, /mcp/setup.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project owner key (ga_...) or an active member key (gm_...). Never print it.",
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
}
},
"required": [
"project_id",
"admin_key"
],
"type": "object"
},
"name": "gate_list_approvers",
"outputSchema": null
},
{
"description": "Read the project's apps, allowed calls, limits, state, idle flags and anomaly-guard settings. Use it to select an app id. Create or revoke apps on the setup endpoint, /mcp/setup.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
}
},
"required": [
"project_id",
"admin_key"
],
"type": "object"
},
"name": "gate_list_apps",
"outputSchema": null
},
{
"description": "Which gateway calls happened recently? Returns recent gateway calls (time, app, matched route, status, reason, duration); use it to investigate individual calls across the project rather than gate_get_metrics aggregates or a single gate_get_run_timeline. Newest first, with totals by status and refusal reason for the returned calls. This view never returns bodies, query values or headers. For 24-hour totals and anomaly scores use gate_get_metrics; for a signed export an auditor can check, gate_export_audit_proof; for one run's history, gate_get_run_timeline.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"app": {
"description": "Optional: only this app id (app_...)",
"type": "string"
},
"limit": {
"description": "How many calls (default 20)",
"maximum": 100,
"minimum": 1,
"type": "integer"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"status": {
"description": "Optional: only this HTTP status, e.g. \"403\"",
"type": "string"
}
},
"required": [
"project_id",
"admin_key"
],
"type": "object"
},
"name": "gate_read_audit",
"outputSchema": null
},
{
"description": "End one run granted with gate_create_run: its token stops working at once (403 run_revoked) while the app itself keeps working. Use it to stop an agent mid-job; grant a new run with gate_create_run if the work should continue.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"run_id": {
"description": "The run id: run.run_id in gate_create_run's result",
"type": "string"
}
},
"required": [
"project_id",
"admin_key",
"run_id"
],
"type": "object"
},
"name": "gate_revoke_run",
"outputSchema": null
},
{
"description": "Apply stored learning suggestions to an existing app and return the applied routes, suggested per-minute limit and learning-session metadata. Review gate_learn_suggestions first, then explicitly confirm; requires the project owner key or an admin member key. mode=\"extend\" adds learned routes (default); \"replace\" removes existing routes before applying them. Both modes set the learned rate limit and keep the app key. Only learned suggestions can be applied: arbitrary routes or rate limits are not accepted, and this tool never starts learning.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project owner key (ga_...) or an accepted admin member key (gm_...). Read it from the .env; never print it.",
"type": "string"
},
"app": {
"description": "The app id (app_...) with stored learning suggestions",
"type": "string"
},
"confirm": {
"description": "Explicit confirmation to apply the reviewed learning suggestions",
"enum": [
true
],
"type": "boolean"
},
"mode": {
"description": "Extend existing routes (default), or replace them with learned routes; both set the suggested rate limit",
"enum": [
"extend",
"replace"
],
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
}
},
"required": [
"project_id",
"admin_key",
"app",
"confirm"
],
"type": "object"
},
"name": "gate_update_app",
"outputSchema": null
},
{
"description": "Is this signed audit export intact? Returns intact or broken_at for a supplied signed export; use it to check a gate_export_audit_proof export rather than retrieve audit rows. Recomputes the chain and project signature; broken_at is a one-based row position. Does not approve actions or change permissions.",
"inputSchema": {
"additionalProperties": false,
"properties": {
"admin_key": {
"description": "The project admin key (ga_...). Read it from the .env; never print it.",
"type": "string"
},
"project_id": {
"description": "The project id from project creation on the setup endpoint (/mcp/setup), e.g. p1a2b3...",
"type": "string"
},
"proof": {
"description": "The full signed export from gate_export_audit_proof",
"type": "object"
}
},
"required": [
"project_id",
"admin_key",
"proof"
],
"type": "object"
},
"name": "gate_verify_audit_proof",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:a7a728a6cede310a1f9024492c46acbeead088331a6a97b09103dc7b3a95bb9a | sha256sum