| name | anarlog |
| description | Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task. |
Anarlog
Use Anarlog's read-only interfaces. Prefer MCP when its tools are connected. Otherwise use the anarlog CLI with --json.
Choose a transport
- If
list_meetings, get_meeting, get_meeting_transcript, and get_recurring_meeting_history are available, use them.
- Otherwise, check
anarlog --version and use CLI commands with --json.
- If neither is available, direct the user to installation. Do not install software unless the user asks.
Never query or modify Anarlog's SQLite database directly. The CLI and MCP server handle application-schema compatibility.
Find the right meeting
- List recent meetings or search by a short title fragment.
- Use a meeting ID returned by the search. Never guess one.
- Get the meeting before requesting its transcript. Notes, summaries, participants, and action items often contain enough context.
- Ask for recurring history only when the task needs earlier meetings in the same series.
See CLI commands and MCP tools.
Keep context bounded
- Request focused transcript pages. Both transports default to 200 words and cap each page at 500 words.
- Follow
next_offset only when you need more transcript context.
- Stop paging once you have enough evidence.
- Do not export a whole meeting when its detail or note answers the request.
