Fathom MCP Server
Connects AI assistants to the Fathom meeting recording API to retrieve meeting summaries, transcripts, and action items.
README
Fathom MCP Server
An MCP (Model Context Protocol) server that connects AI assistants to the Fathom meeting recording API. Retrieve meeting summaries, transcripts, and action items directly from your AI tools.
Available Tools
| Tool | Description |
|---|---|
fathom_list_meetings |
List meetings with filters (date range, recorder, team, domain) |
fathom_get_meeting_summary |
Get AI-generated summary for a specific recording |
fathom_get_meeting_transcript |
Get full transcript with speaker names and timestamps |
fathom_get_meeting_details |
Get summary + action items + optional transcript in one call |
fathom_list_teams |
List all teams in the Fathom organization |
Prerequisites
- Python 3.10+
- A Fathom API key (requires a Fathom account)
Setup
-
Clone the repo:
# Note: This repo will be moved to the withflex org at a later time git clone https://github.com/stussy446/fathom-mcp.git cd fathom-mcp -
Create a virtual environment and install dependencies:
python -m venv .venv .venv/bin/pip install -e . -
Get your Fathom API key from Fathom Settings > API.
Adding to Claude Code
Add the following to your ~/.claude.json file under the top-level mcpServers key:
"mcpServers": {
"fathom": {
"command": "/path/to/fathom-mcp/.venv/bin/python",
"args": ["server.py"],
"cwd": "/path/to/fathom-mcp",
"env": {
"FATHOM_API_KEY": "your_api_key_here"
}
}
}
Replace /path/to/fathom-mcp with the actual path where you cloned the repo.
Adding to Claude Desktop
Add the following to ~/Library/Application Support/Claude/claude_desktop_config.json:
"mcpServers": {
"fathom": {
"command": "/path/to/fathom-mcp/.venv/bin/python",
"args": ["/path/to/fathom-mcp/server.py"],
"env": {
"FATHOM_API_KEY": "your_api_key_here"
}
}
}
Note: Claude Desktop does not support the
cwdfield, so use the full path toserver.pyin theargs.
Usage
Once configured, just ask your AI assistant naturally:
- "Show me my recent meetings"
- "Get the summary for recording 12345"
- "What were the action items from my last call?"
- "List my Fathom teams"
API Reference
All requests go to https://api.fathom.ai/external/v1 with X-Api-Key header authentication. Rate limit is 60 requests per 60 seconds.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。