Skip to main content
Glama

Fathom AI MCP

Ask DeepWiki npm version License: MIT Node.js TypeScript GitHub stars

Buy Me A Coffee

A Model Context Protocol server for the Fathom AI meeting intelligence API. Responses are optimized for LLM consumption - compact plaintext instead of raw JSON, with playback URLs stripped and transcripts chunked by time window.

fathom-ai-mcp MCP server

Tools

Tool

Description

list_meetings

List meetings with filtering by date, team, domain, participant, and pagination

get_transcript

Get transcript for a recording, with optional time-window chunking (start_time/end_time)

get_summary

Get AI-generated summaries for one or more recordings (clean markdown, no playback URLs)

list_teams

List all teams

list_team_members

List team members, optionally filtered by team

All list tools support page and page_size params with random page access (no sequential fetching required). Use participants on list_meetings to filter by user email.

Related MCP server: Offorte Proposal Software

Prerequisites

  1. Install Node.js (v20+).

  2. Get a Fathom API key: go to Fathom Settings > API Access > Add + > Generate API Key.

Installation

Option 1: Claude Desktop

  1. Download fathom-ai-mcp.mcpb from Releases

  2. Open the .mcpb file with Claude Desktop to install

  3. Configure your Fathom API key in Claude Desktop's extension settings

Option 2: Manual Configuration

Add the following to your MCP client configuration:

{
  "mcpServers": {
    "Fathom": {
      "command": "npx",
      "args": ["-y", "@jerichosequitin/fathom-ai-mcp"],
      "env": {
        "FATHOM_API_KEY": "your-api-key"
      }
    }
  }
}

Config file locations:

  • Claude Desktop: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

  • Cursor: .cursor/mcp.json in your project root

  • Windsurf: ~/.codeium/windsurf/mcp_config.json

Claude Code

claude mcp add Fathom -e FATHOM_API_KEY=your-api-key -- npx @jerichosequitin/fathom-ai-mcp

Environment Variables

Variable

Required

Description

FATHOM_API_KEY

Yes

Your Fathom API key

For Developers

Setup

git clone https://github.com/jerichosequitin/fathom-ai-mcp.git
cd fathom-ai-mcp
npm install
npm run build
npm start

Scripts

Command

Description

npm run build

Compile TypeScript

npm run validate

Type-check + lint + format check

npm run lint:fix

Auto-fix lint issues

npm run format

Auto-format with Prettier

npm run mcpb:build

Build MCPB package for Claude Desktop

Building MCPB Package

npm run mcpb:build

Creates fathom-ai-mcp-{version}.mcpb ready for GitHub Releases.

License

This project is licensed under the MIT License.

Available Tools

5 tools
get_summaryB

Get summaries for one or more meeting recordings. Returns clean markdown with playback URLs stripped.

Inputs: recording_ids (required).

get_transcriptA

Get the transcript for a meeting recording. Returns plaintext lines.

For long meetings, use start_time/end_time to fetch a specific window. First call without time params to get metadata (duration, line count), then request specific chunks as needed.

Inputs: recording_id (required), end_time, start_time.

list_meetingsA

List meetings with optional filtering and pagination. All timestamps are UTC. Use get_summary or get_transcript for detailed content.

Inputs: page, teams, page_size, recorded_by, +7 more.

list_team_membersC

List team members, optionally filtered by team name.

Inputs: page, team, page_size.

list_teamsC

List all teams.

Inputs: page, page_size.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool targets a distinct resource or action: summaries, transcripts, meetings list, team members, teams. No overlap in purpose.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern (get_*, list_*), making the set predictable and easy to navigate.

    Tool Count5/5

    With 5 tools, the surface is well-scoped for a meeting information retrieval server, covering the core read operations without excess.

    Completeness4/5

    The tools cover listing and retrieving meeting details, transcripts, and team info. Minor gaps like search or filtering capabilities might exist but do not hinder basic workflows.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers