What can you do with this server?

The Fathom AI MCP server provides programmatic access to Fathom AI's meeting intelligence API, with tools optimized for LLM consumption: * List Meetings (list_meetings): Browse recorded meetings with filtering by date range, team names, participant/recorder emails, meeting type (internal/external), and invitee domains. Supports pagination with random page access. * Get Transcript (get_transcript): Retrieve full plaintext transcripts for a specific recording. Supports time-window chunking via start_time/end_time (HH:MM:SS) to fetch portions of long meetings. * Get Summary (get_summary): Fetch AI-generated summaries for one or more recordings in clean markdown format, with playback URLs stripped. Supports batch retrieval. * List Teams (list_teams): Enumerate all teams in your Fathom organization with pagination support. * List Team Members (list_team_members): Retrieve team members across your organization, with optional filtering by team name and pagination support.

Which integrations are available for this server?

Provides tools for interacting with the Fathom AI meeting intelligence API, enabling AI agents to list meetings, retrieve transcripts with time-window chunking, and access AI-generated summaries.

Fathom AI MCP

by jerichosequitin

Overview Schema Related Servers Score Discussions

TypeScript

Remote

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

Install Node.js (v20+).
Get a Fathom API key: go to Fathom Settings > API Access > Add + > Generate API Key.

Installation

Option 1: Claude Desktop

Download fathom-ai-mcp.mcpb from Releases
Open the .mcpb file with Claude Desktop to install
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.

ParametersJSON Schema

Name	Required	Description	Default
`recording_ids`	Yes	One or more recording IDs (from list_meetings).

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only mentions the output format (markdown without playback URLs), but does not cover idempotency, authorization needs, rate limits, or any side effects. This is insufficient for a retrieval tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, no redundant words. Every sentence contributes meaning: the first states the action and resource, the second details the output. Ideal conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has one simple parameter and no output schema. The description explains the input origin and output format, which is adequate but not exhaustive. It lacks details on limits (max recordings) or whether results are paginated, but is sufficient for basic usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with one parameter. The description adds value by noting that recording IDs come from 'list_meetings', which clarifies the parameter source beyond the schema's own description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get summaries' and the resource 'meeting recordings', and specifies the output format (clean markdown with playback URLs stripped). It implicitly differentiates from the sibling 'get_transcript' by focusing on summaries rather than verbatim transcript, but does not explicitly contrast them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'get_transcript' or other siblings. There are no prerequisites or context for appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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.

ParametersJSON Schema

Name	Required	Description
`end_time`	No	End of time window in HH:MM:SS format (e.g. "00:20:00").
`start_time`	No	Start of time window in HH:MM:SS format (e.g. "00:10:00").
`recording_id`	Yes	The recording ID (from list_meetings).

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description discloses key behaviors: returns plaintext lines, metadata on first call without time params, and ability to request chunks. Lacks details on error handling or processing state, but sufficient for a read-only tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five sentences total, no redundancy. Front-loaded with main purpose, followed by concise usage notes. Every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, so description should detail return structure. It says 'plaintext lines' and hints at metadata fields (duration, line count) but does not fully specify format or what 'plaintext lines' means. Adequate but could be more complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds significant value by explaining the usage pattern (first call for metadata, then chunks). For recording_id, it references list_meetings, consistent with schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the function: 'Get the transcript for a meeting recording. Returns plaintext lines.' Distinguishes well from sibling tools like get_summary and list_meetings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance on using start_time/end_time for long meetings and a two-call strategy to first fetch metadata. Does not explicitly contrast with siblings, but the context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_meetingsA

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

ParametersJSON Schema

Name	Required	Description	Default
`page`	No	Page number (starts at 1). Any page can be requested directly.
`teams`	No	Filter by team names.
`page_size`	No	Number of meetings per page (default 10).
`recorded_by`	No	Filter by recorder email addresses.
`meeting_type`	No	Filter by 'internal' or 'external'.
`participants`	No	Filter by participant email addresses (calendar invitees and recorder). Use with participants_match to control matching logic.
`created_after`	No	ISO timestamp to filter meetings created after this date.
`created_before`	No	ISO timestamp to filter meetings created before this date.
`participants_match`	No	How to match participants: 'any' returns meetings with at least one match, 'all' returns only meetings where every listed participant is present.	any
`calendar_invitees_domains`	No	Filter by invitee email domains (e.g. ["acme.com"]).
`calendar_invitees_domains_type`	No	Filter invitee type: 'all', 'only_internal', or 'one_or_more_external'.

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the burden of behavioral disclosure. It mentions timestamps are UTC and implies pagination, but does not disclose whether the tool is read-only, rate limits, or any destructive aspects. The description is adequate but lacks deeper behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the main purpose and features, and provides guidance in the second. Every word adds value, with no redundancy. Highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 11 documented parameters and no output schema, the description is minimal. It covers the basic purpose and points to alternatives, but lacks details on return format, pagination details (e.g., total pages), or ordering. For a complex filtering tool, more context would be helpful, but it is not incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds no additional parameter meaning beyond what the schema already provides (e.g., 'optional filtering and pagination' is already evident from the schema). It does not enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists meetings with optional filtering and pagination, and distinguishes from siblings by directing to get_summary/get_transcript for detailed content. The verb 'list' and resource 'meetings' are explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description advises using get_summary or get_transcript for detailed content, indicating when not to use this tool. However, it does not address when to use this tool versus other sibling tools like list_teams, though those are for different resources. The guidance is clear but lacks explicit exclusions for all alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_team_membersC

List team members, optionally filtered by team name.

ParametersJSON Schema

Name	Required	Description
`page`	No	Page number (starts at 1). Any page can be requested directly.
`team`	No	Team name to filter by.
`page_size`	No	Number of members per page (default 10).

TDQS

C2.8/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not mention pagination, result format, or side effects, leaving the agent uncertain about how the tool behaves beyond listing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, which is concise but lacks detail beyond the name and a basic filter. It is adequate but does not earn its place with extra value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and three parameters, the description is incomplete. It fails to explain pagination behavior or result expectations, which are critical for tool selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds minor context by noting the team filter is optional, but this is already implied by the schema's non-required parameter. No significant additional meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'list' and the resource 'team members', with an optional filter by team name. It is specific but does not explicitly differentiate from sibling tools like 'list_teams', which lists teams rather than members.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, such as when to filter vs retrieve all members, nor are any exclusions or prerequisites mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_teamsC

List all teams.

ParametersJSON Schema

Name	Required	Description	Default
`page`	No	Page number (starts at 1). Any page can be requested directly.
`page_size`	No	Number of teams per page (default 10).

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description bears full responsibility for behavioral disclosure. It only states 'List all teams,' omitting any indication of pagination (though schema covers it), potential rate limits, authentication requirements, or data freshness. The description adds no behavioral context beyond the minimal verb and resource.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at just four words, with no extraneous information. While effective, it could benefit from a bit more context (e.g., 'paginated list') without becoming verbose. The front-loading is good.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple nature of a list tool with pagination handled by the schema, the description is adequate for basic use. However, it lacks details on output format (e.g., returns an array of team objects) and does not differentiate from sibling list tools like 'list_meetings', making it slightly less complete for an agent that needs to decide between them.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage for both parameters (page and page_size) with clear descriptions and defaults. The tool description adds no additional meaning beyond what the schema already provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'List all teams' clearly specifies the verb (list) and resource (teams), indicating a straightforward retrieval operation. However, it doesn't differentiate from sibling tools like 'list_team_members' or 'list_meetings', which also list resources, but the distinct resource name makes it unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as 'get_summary' or 'list_team_members'. There is no mention of context, prerequisites, or exclusions, leaving the agent to infer usage without help.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

5 tool updatesMay 1, 2026
- Addedget_summary
- Addedget_transcript
- Addedlist_meetings
- Addedlist_team_members
- Addedlist_teams
5 tool updatesv0.1.2May 1, 2026
- Removedget_summary
- Removedget_transcript
- Removedlist_meetings
- Removedlist_team_members
- Removedlist_teams
5 tool updatesv0.2.0Mar 21, 2026
- First observedget_summary
- First observedget_transcript
- First observedlist_meetings
- First observedlist_team_members
- First observedlist_teams

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.7/5.0

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

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

mcp AOAuth
com.mux
The official MCP Server for the Mux API
Multimedia Processing Entertainment & Media API Testing
22168
mcpOAuth
com.bullpenstrategygroup.rotunda
An MCP server that provides congressional transcripts
Government Data Search Open Data
2
RiverScript A
com.riverscript
MCP server for RiverScript, an AI transcription platform - fetches transcripts shared via a link.
Audio Processing AI & Machine Learning
11
smithery-ai-cookbook-python-quickstart
ai.smithery
A simple MCP server built with FastMCP and python
Developer Tools
213

Related MCP Servers

mcp-perplexity
Search RAG Systems
daniel-lxs
A
license
Not graded
quality
C
maintenance
MCP Server for the Perplexity API.
Updated 2 years ago (2025-02-27 16:28 UTC)
66
MIT
Offorte Proposal Softwareofficial
App Automation Marketing Content Management Systems
offorte
A
license
B
quality
C
maintenance
MCP server for the Offorte API - Create & send proposals using AI
Updated 6 months ago (2026-03-19 14:36 UTC)
15
20
5
MIT
Fathom-Simple-MCP
Calendar Management Search Workplace & Productivity
druellan
A
license
A
quality
A
maintenance
A Model Context Protocol (MCP) server for accessing Fathom AI API endpoints (meetings, recordings, transcripts, summaries, teams, team members) via GET operations.
Updated a month ago (2026-07-28 15:09 UTC)
6
2
MIT
fireflies-mcp
Text Summarization Search Workplace & Productivity
evans-sam
F
license
Not graded
quality
D
maintenance
MCP server and CLI for Fireflies.ai API to retrieve transcripts, search meetings, and generate summaries.
Updated 6 months ago (2026-03-20 03:19 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jerichosequitin/fathom-ai-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

Fathom AI MCP

Tools

Prerequisites

Installation

Option 1: Claude Desktop

Option 2: Manual Configuration

Claude Code

Environment Variables

For Developers

Setup

Scripts

Building MCPB Package

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Offorte Proposal Softwareofficial

Latest Blog Posts

MCP directory API