MCP for agents

The local MCP server runs inside the anarlog executable and communicates over standard input and output. It opens no port and sends no meeting data to Anarlog’s servers. Open the desktop app once so it can create the database. The app does not need to stay open after that.

Configure a client

Use this generic MCP configuration:

{
  "mcpServers": {
    "anarlog": {
      "command": "anarlog",
      "args": ["mcp"]
    }
  }
}

If anarlog is not on the client’s PATH, use the executable’s absolute path as command. Restart the client after changing its configuration. For a custom database path:

{
  "mcpServers": {
    "anarlog": {
      "command": "anarlog",
      "args": ["--db-path", "/path/to/app.db", "mcp"]
    }
  }
}

Use tools deliberately

Start with list_meetings, then pass a returned id to get_meeting. Call get_meeting_transcript only when the notes and summaries do not answer the question. Transcript pages default to 200 words and cap at 500. Follow pagination.next_offset only when you need more context. Use get_recurring_meeting_history with a known meeting ID when a task depends on earlier meetings in the same series. To persist an edit, call propose_summary_edit or propose_memo_edit. The tool returns a pending proposal. Do not claim the meeting changed. Use list_proposals and get_proposal to inspect staged work. decline_proposal discards a pending proposal. See the MCP reference for exact parameters and resources.

Getting started

Using Anarlog

AI and privacy

CLI and agents

Recipes

Reference

Help

Configure a client

Use tools deliberately

​Configure a client

​Use tools deliberately

Configure a client

Use tools deliberately