patterns.list · Cortex MCP Docs

Description

Per ADR-0021 §read-API Family D.

Input schema

Field	Type	Required	Description
`counterparty_id`	`string`	no	Filter to a single counterparty.
`pattern_class`	`'communication' \| 'schedule' \| 'preference' \| 'commitment' \| 'trust'`	no	Filter by pattern class.
`since`	`string (ISO-8601)`	no	Lower bound on detected_at.
`limit`	`integer`	no	Default 25; max 100.

Output shape

typescript

{ items: Array<{ pattern_class: string; summary: string; confidence: 'strong_pattern' | 'pretty_sure' | 'just_guessing'; evidence_episode_ids: string[]; world_version: string }> }

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": "patterns.list", "arguments": { "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

{
  "items": [
    { "pattern_class": "communication", "summary": "Sarah replies within 2 hours during work hours.", "confidence": "strong_pattern", "evidence_episode_ids": ["ep_01H..."], "world_version": "wv_01HXR4WORLD" }
  ]
}

Errors this tool can return

Code	Meaning
`invalid_arguments`	Tool input failed Zod validation.
`unauthorized`	Missing or invalid bearer token.
`quota_exceeded`	Per-minute, daily call, or daily inference budget exceeded.

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