FathomBridge

FathomBridge

Connects AI tools to Fathom meeting transcripts, summaries, and action items via a single API key.

Category
访问服务器

README

🌉 FathomBridge

Your meetings, in your AI.

FathomBridge is a zero-install MCP (Model Context Protocol) server that connects any AI CLI or IDE directly to your Fathom meeting transcripts, summaries, and action items — using your API key.

No cloning. No building. One line of config.

npm version License: MIT MCP Compatible


✨ Features

  • 📋 List meetings — with date, team, and pagination filters
  • 📝 Full transcripts — speaker-labelled with timestamps
  • 🤖 AI summaries — key points and decisions
  • Action items — with owners and due dates
  • 🔍 Smart search — find any meeting by title, host, or participant
  • 👥 Teams — list your Fathom organization teams
  • Zero install — runs via npx, nothing to clone or build
  • 🔑 API key auth — simple, local, no OAuth flow needed

🚀 Quick Start

Step 1 — Get Your Fathom API Key

  1. Log in to fathom.video
  2. Go to Settings → Integrations → API
  3. Copy your API key

Step 2 — Add to Your AI Tool Config

Claude Code (~/.claude/claude.json):

{
  "mcpServers": {
    "fathom": {
      "command": "npx",
      "args": ["-y", "fathombridge"],
      "env": {
        "FATHOM_API_KEY": "your-api-key-here"
      }
    }
  }
}

Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "fathom": {
      "command": "npx",
      "args": ["-y", "fathombridge"],
      "env": {
        "FATHOM_API_KEY": "your-api-key-here"
      }
    }
  }
}

Windsurf (~/.codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "fathom": {
      "command": "npx",
      "args": ["-y", "fathombridge"],
      "env": {
        "FATHOM_API_KEY": "your-api-key-here"
      }
    }
  }
}

Gemini CLI (~/.gemini/settings.json):

{
  "mcpServers": {
    "fathom": {
      "command": "npx",
      "args": ["-y", "fathombridge"],
      "env": {
        "FATHOM_API_KEY": "your-api-key-here"
      }
    }
  }
}

Step 3 — Restart Your AI Tool

Restart Claude Code / Cursor / Windsurf and verify:

/mcp

You should see fathom listed as connected.


🛠️ Available Tools

Tool Description
list_meetings List meetings with date/team filters
get_transcript Full transcript with speaker labels
get_summary AI summary + key points
get_action_items Action items with owners/due dates
search_meetings Search by title, host, participant
list_teams List organization teams

💬 Example Prompts

Once connected, try these in your AI tool:

Show me my last 5 Fathom meetings

Get the transcript from my sprint planning call yesterday

What were the action items from the client call with John?

Search for all meetings about the Q3 roadmap

Show me all meetings from this week with action items

Get the summary of meeting ID abc123

🔒 Security

  • Your API key is stored only in your local MCP config
  • All requests go directly from your machine to Fathom's API
  • No data is stored, logged, or transmitted to any third party
  • Never commit your API key to version control

🔧 Troubleshooting

fathom not showing in /mcp → Restart your AI tool after editing the config file

Error: FATHOM_API_KEY environment variable is required → Make sure the env block in your config has your actual API key

Error: 401 Unauthorized → Your API key is invalid — regenerate it at fathom.video → Settings → API

No meetings found → Your API key only accesses meetings recorded by you or shared to your team

Transcript not available yet → Fathom takes a few minutes to process transcripts after a call ends


📋 Requirements

  • Node.js 18 or higher
  • A Fathom account
  • A Fathom API key

🤝 Contributing

Contributions welcome! Please:

  1. Fork the repo
  2. Create a feature branch
  3. Make your changes with tests
  4. Submit a PR with a clear description

📄 License

MIT © 2026 Nauman Pathan


🙏 Acknowledgements

Built on top of the Model Context Protocol by Anthropic. Powered by Fathom.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选