Tool reference · Edit, history & reports
memory_extract_session
Lists, reads and marks as processed the transcripts of past sessions that were captured automatically, so knowledge can be extracted from them.
local stdio server writes
When to use
- At the start of a session, to check whether earlier sessions still have unextracted knowledge.
- You want to review a past conversation and save its decisions and fixes with memory_save.
- You finished extracting a transcript and want it removed from the pending list.
Parameters
| Name | Type | Default | Description |
|---|---|---|---|
actionrequired | "list" | "get" | "complete" | — | list: show pending sessions. get: return transcript data. complete: mark as done. |
session_id | string | — | Session ID (required for 'get' and 'complete') |
chunk | integer | 0 | Chunk number for large transcripts (0-based) |
Example
Arguments
{
"action": "list"
}Result shape
{
"pending": 1,
"sessions": [
{
"session_id": "a1b2c3",
"project_name": "my-api",
"started_at": "2026-09-20T09:58:12Z",
"ended_at": "2026-09-20T11:40:03Z",
"stats": {},
"file_size_kb": 84.2
}
]
}action 'get' returns the transcript (in 100 KB chunks when large); action 'complete' returns { completed: true, session_id }.
Values are illustrative; the keys follow the server's handler. MCP clients receive the result as JSON text content.
Server description
The description the server sends to your agent in tools/list, captured from the v14.7.0 source:
Get pending session transcripts for knowledge extraction. Previous sessions are auto-captured on exit. Use action='list' to see pending, 'get' to read transcript, then save knowledge via memory_save, then 'complete' to mark as processed.