Provides access to Fathom AI API endpoints for managing meeting data, including retrieving meetings with filtering options, accessing transcripts and summaries for recordings, and managing teams and team members.
Fathom MCP Server
A Model Context Protocol (MCP) server for accessing Fathom AI API endpoints (meetings, recordings, transcripts, summaries, teams, team members) via GET operations. Built with FastMCP.
This implementation provides streamlined access to Fathom meeting data while minimizing API consumption. It is optimized for efficiency and simplicity.
Features
List Meetings: Retrieve meetings with optional filtering and inclusion of transcripts/summaries
Get Summary: Retrieve markdown summary for a specific recording
Get Transcript: Retrieve transcript for a specific recording
List Teams: Retrieve all teams
List Team Members: Retrieve team members with optional team filtering
Requirements
Python 3.10+
Fathom API key
FastMCP 2.0+
Installation
Clone or download this repository
Install dependencies:
or
Configuration
The server uses environment variables for configuration:
FATHOM_API_KEY
: Your Fathom API key (required)FATHOM_TIMEOUT
: Request timeout in seconds (default: 30)
Usage
Direct Python Execution (Recommended)
Using UV
Available Tools
list_meetings
Retrieve meetings with optional filtering and pagination.
Properties:
calendar_invitees
(list[str], optional): Filter by invitee emailscalendar_invitees_domains
(list[str], optional): Filter by domainscalendar_invitees_domains_type
(str, optional): Domain filter type (all, only_internal, one_or_more_external)created_after
(str, optional): ISO timestamp filtercreated_before
(str, optional): ISO timestamp filtercursor
(str, optional): Pagination cursorinclude_action_items
(bool, optional): Include action itemsinclude_crm_matches
(bool, optional): Include CRM matchesinclude_summary
(bool, optional): Include summaryinclude_transcript
(bool, optional): Include transcriptrecorded_by
(list[str], optional): Filter by recorder emailsteams
(list[str], optional): Filter by team names
get_summary
Retrieve markdown summary for a recording.
Properties:
recording_id
(int): The recording identifierdestination_url
(str, optional): Async callback URL
get_transcript
Retrieve transcript for a recording.
Properties:
recording_id
(int): The recording identifierdestination_url
(str, optional): Async callback URL
list_teams
Retrieve teams with optional pagination.
Properties:
cursor
(str, optional): Pagination cursor
list_team_members
Retrieve team members with optional filtering and pagination.
Properties:
cursor
(str, optional): Pagination cursorteam
(str, optional): Filter by team name
Output Format
All tools return data in filtered JSON format for improved readability and LLM processing. The output is filtered to remove empty, null or redundant information.
Example JSON output for meetings:
Error Handling
The server provides comprehensive error handling:
401 Unauthorized: Invalid API key
404 Not Found: Resource not found
429 Rate Limited: Too many requests
500 Server Error: Fathom API issues
All errors are logged via MCP context with appropriate severity levels.
Security
API keys are loaded from environment variables
No sensitive data is logged
HTTPS is used for all API requests
Error messages don't expose internal details
License
MIT License.
A Model Context Protocol (MCP) server for accessing Fathom AI API endpoints (meetings, recordings, transcripts, summaries, teams, team members) via GET operations.