memory.correct · Cortex MCP Docs

Description

Records a correction against an existing episode. Corrections do not overwrite — Cortex keeps the original observation and the corrected text linked, so reversals and contradictions are auditable.

Input schema

Field	Type	Required	Description
`episode_id`	`string`	yes	Episode ID to correct.
`correction`	`string`	yes	Corrected content or summary.
`reason`	`string`	no	Optional reason for the correction.

Output shape

typescript

{
  ok: boolean;
  error?: 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": "memory.correct",
  "arguments": {
    "episode_id": "ep_01HXR4N9TZ5W2QF6KMVDX8Y3GP",
    "correction": "Sarah leads the Platform team at Acme (not API).",
    "reason": "Confirmed in 1:1 on 2026-05-27"
  }
}

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

{ "ok": true }

Errors this tool can return

Code	Meaning
`invalid_arguments`	Tool input failed Zod validation.
`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).