Skip to main content
Glama

migas-mcp

MCP server for Migas meeting transcripts. Query your local meeting data from Claude Desktop, Claude Code, Cursor, or any MCP-compatible AI assistant.

What it does

Migas transcribes your meetings locally on your Mac. This MCP server gives AI assistants read-only access to that data so you can ask questions like:

  • "What did we discuss about the roadmap last week?"

  • "What has Sarah said about the budget across all meetings?"

  • "Show me the transcript from yesterday's standup"

Related MCP server: transcripts

Tools

Tool

Description

list_meetings

Recent meetings with title, date, duration, participants

get_meeting_transcript

Full speaker-labeled transcript for a meeting

search_transcripts

Full-text search across all meeting transcripts

find_speakers

Look up enrolled speakers by name

get_speaker_contributions

Everything a speaker said across all meetings

Install

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "migas": {
      "command": "npx",
      "args": ["-y", "migas-mcp"]
    }
  }
}

Claude Code

claude mcp add migas -- npx -y migas-mcp

Cursor

Add to MCP settings:

{
  "mcpServers": {
    "migas": {
      "command": "npx",
      "args": ["-y", "migas-mcp"]
    }
  }
}

Requirements

  • Migas installed and launched at least once (creates the local database)

  • macOS (reads from ~/Library/Application Support/Migas/meetings.db)

Privacy

The MCP server is read-only and connects to your local Migas database. No meeting data is sent anywhere by the server itself. When you ask an AI assistant a question, only the relevant transcript text is sent to the AI provider, same as using Migas's built-in chat.

Development

bun install
bun test
bun run build

Available Tools

5 tools
find_speakersA

Look up enrolled speakers by name. Returns candidates with IDs for use with get_speaker_contributions. Only returns speakers with stable cross-meeting identities (not transient per-meeting guests).

Inputs: name (required).

get_meeting_transcriptA

Get the full transcript for a specific meeting with speaker labels and timestamps.

Inputs: meeting_id (required).

get_speaker_contributionsA

Get everything a specific enrolled speaker said across all meetings. Use find_speakers first to get the speaker ID.

Inputs: speaker_id (required).

list_meetingsA

List recent meetings with title, date, duration, and participant names.

Inputs: limit, since_date.

search_transcriptsA

Search across all meeting transcripts using full-text search. Returns matching segments with meeting context and speaker attribution.

Inputs: query (required), limit, meeting_id.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: listing meetings, retrieving a transcript, searching transcripts, finding speakers, and aggregating speaker contributions. There is no functional overlap or ambiguity between tools.

    Naming Consistency5/5

    All tool names follow the same verb_noun pattern in snake_case (e.g., list_meetings, get_meeting_transcript, search_transcripts), which makes the naming scheme predictable and consistent across the entire set.

    Tool Count5/5

    Five tools is a well-scoped count for a meeting transcription and speaker analytics server. Each tool covers a distinct functional area without redundancy or excessive granularity.

    Completeness5/5

    The server provides complete coverage of its core domain: browsing meetings, reading transcripts, full-text search, and per-speaker contribution analysis. There are no obvious gaps or dead ends in the workflow.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables an AI agent to list, read, and search local meeting transcript files, returning structured transcript information and search hits. The server enforces read-only access confined to a transcripts directory with .txt and .md files only.
      -
    • A
      license
      A
      quality
      C
      maintenance
      Exposes meeting transcripts to any MCP-capable AI client so it can list meetings, page through a single transcript, and search across all of them for a topic with exact timestamps. Speaker labels, emails, phone numbers, and paths are pseudonymized or redacted before anything crosses the protocol, and transcripts are read-only.
      3
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Provides read-only access to what you have dictated and what was said in your recorded meetings, so coding agents like Codex, Claude Code, Pi or LM Studio can search your local transcripts and notes.
      MIT