whoop-mcp

whoop-mcp

A Model Context Protocol (MCP) server that gives Claude access to your WHOOP biometric data — recovery, sleep, strain, and workouts.

Category
访问服务器

README

whoop-mcp

A Model Context Protocol (MCP) server that gives Claude access to your WHOOP biometric data — recovery, sleep, strain, and workouts.

Ask Claude things like:

  • "How's my recovery today?"
  • "How did I sleep last night?"
  • "How has my HRV trended this week?"
  • "What was my strain from yesterday's workout?"

Privacy

This app accesses your WHOOP data locally on your device. No data is sent to any third-party server.


Tools

Tool What it returns
get_recovery Recovery score, HRV, resting HR, SpO2
get_sleep Sleep duration, stages (light/deep/REM), efficiency, respiratory rate
get_strain Day strain score, avg/max HR, calories
get_latest_workout Most recent workout — sport, duration, strain, HR zones
get_recovery_trend Recovery scores over N days (default 7)
get_sleep_trend Sleep data over N days (default 7)
get_workout_history Recent workout history (default 5)
get_profile Profile + body measurements

Setup

1. Create a WHOOP developer app

  1. Go to developer-dashboard.whoop.com
  2. Sign in with your WHOOP account
  3. Create a new App:
    • Name: whoop-mcp (or anything)
    • Redirect URI: http://localhost:8080/callback
    • Scopes: select all read scopes + offline
  4. Copy your Client ID and Client Secret

2. Install

npm install -g @souravpn/whoop-mcp

3. Run one-time auth setup

This opens your browser, you log into WHOOP, and your tokens are saved to ~/.whoop-mcp-tokens.json:

WHOOP_CLIENT_ID=your_id WHOOP_CLIENT_SECRET=your_secret whoop-mcp-auth-setup

You only need to do this once. The server will auto-refresh tokens after that.

4. Add to Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "whoop": {
      "command": "@souravpn/whoop-mcp",
      "env": {
        "WHOOP_CLIENT_ID": "your_client_id",
        "WHOOP_CLIENT_SECRET": "your_client_secret"
      }
    }
  }
}

Restart Claude Desktop. You should see a green "running" badge in Settings → Developer.

5. Test it

Open a new chat and ask:

How's my recovery today?

Example queries

Daily check-in:

What's my recovery, sleep, and strain for today?

Trend analysis:

How has my HRV trended over the past 7 days?

Workout correlation:

Look at my workouts this week and my recovery scores
the day after each one. Is there a pattern?

Full briefing:

Give me a complete health briefing — recovery, last
night's sleep breakdown, and any workouts from yesterday

Pairing with Oura

If you also use Oura Ring, you can run both MCP servers together and ask Claude to cross-reference:

{
  "mcpServers": {
    "whoop": {
      "command": "/path/to/whoop-mcp",
      "env": { "WHOOP_ACCESS_TOKEN": "your_whoop_token" }
    },
    "oura": {
      "command": "/path/to/oura-mcp",
      "env": { "OURA_ACCESS_TOKEN": "your_oura_token" }
    }
  }
}

Then ask:

Compare my WHOOP and Oura HRV readings for this week.
Do they agree? Which is trending higher?

Development

git clone https://github.com/yourusername/whoop-mcp
cd whoop-mcp
npm install
npm run build

# Test locally
WHOOP_ACCESS_TOKEN=your_token node dist/index.js

Project structure

whoop-mcp/
├── src/
│   ├── index.ts   # MCP server + tool definitions
│   └── whoop.ts   # WHOOP API client + formatters
├── package.json
├── tsconfig.json
└── README.md

Contributing

PRs welcome. Some ideas for extension:

  • Heart rate time series data
  • Sleep stage timeline (light/deep/REM per hour)
  • Strain goal recommendations
  • Weekly summary tool

License

MIT


Acknowledgements

Built with the MCP TypeScript SDK and the WHOOP Developer API.

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