trust.check · Cortex MCP Docs

Description

Returns the autonomy level (1, 2, or 3) for a given action class and optional counterparty. Use this before invoking an action to predict whether it will execute or queue for approval.

Input schema

Field	Type	Required	Description
`action_class`	`string`	yes	Action class to check (e.g. `communicate`, `schedule`).
`counterparty_id`	`string`	no	Optional counterparty identifier.

Output shape

typescript

{
  autonomy_level: 1 | 2 | 3;
  granted_via: string;
  action_class: string;
}

Level 1 = inform-only (surfaces intent, no action executes). Level 2 = suggest with approval (queues for user confirmation before acting). Level 3 = act-then-summarize (executes immediately, notifies after). Levels graduate per-(action × counterparty), never globally.

Example call

JSON-RPC tools/call request body (omit the JSON-RPC envelope when using an SDK; the SDK adds it for you):

jsontools/call params

{
  "name": "trust.check",
  "arguments": {
    "action_class": "communicate",
    "counterparty_id": "entity_01HXSARAH"
  }
}

Example response

Tool results are always wrapped as content[0].text with a stringified JSON body. The shape below is what you get back from JSON.parse(result.content[0].text):

jsonparsed result body

{
  "autonomy_level": 2,
  "granted_via": "earned_2026-04-18",
  "action_class": "communicate"
}

Errors this tool can return

Code	Meaning
`unauthorized`	Missing or invalid bearer token.

See the full error catalog for resolution steps on each code, plus the standard transport-layer responses (401, 429).