Whoop MCP Server
Enables Claude to access and analyze Whoop health data including recovery, sleep, strain, and workouts through a custom MCP connector.
README
Whoop MCP Server
A Model Context Protocol (MCP) server that connects your Whoop health data to Claude. Designed to be hosted remotely and used as a custom connector in Claude.ai.
Built using the Whoop Developer API v2.
Features
- Recovery Data: Daily recovery scores, HRV, resting heart rate, SpO2, skin temperature
- Sleep Analysis: Sleep duration, stages, efficiency, performance, respiratory rate
- Strain Tracking: Daily strain scores, calories burned, heart rate zones
- Workout History: All logged workouts with detailed metrics
- Auto-Sync: Automatically keeps data fresh with smart sync logic
- 90-Day History: Maintains local cache of your health data for trend analysis
MCP Tools
| Tool | Description |
|---|---|
get_today |
Morning briefing with recovery, sleep, and strain |
get_recovery_trends |
Recovery patterns over time with HRV/RHR |
get_sleep_analysis |
Sleep quality trends and stage breakdowns |
get_strain_history |
Training load and calorie trends |
sync_data |
Manually trigger a data sync |
get_auth_url |
Get authorization URL for Whoop connection |
Setup
1. Create a Whoop Developer App
- Go to developer.whoop.com
- Create a new application
- Note your Client ID and Client Secret
- Set the redirect URI to your deployed server's callback URL (e.g.,
https://your-app.railway.app/callback)
2. Deploy to Railway
- Fork/push this repo to GitHub
- Create a new project on Railway
- Connect your GitHub repo
- Add environment variables:
WHOOP_CLIENT_ID: Your Whoop app client IDWHOOP_CLIENT_SECRET: Your Whoop app client secretWHOOP_REDIRECT_URI:https://your-app.railway.app/callback
- Add a volume mounted at
/datafor persistent SQLite storage - Deploy!
3. Authorize with Whoop
- Visit
https://your-app.railway.app/healthto verify it's running - The first time you use the
get_auth_urltool in Claude, it will provide an authorization link - Visit the link, log in to Whoop, and authorize the app
- You'll be redirected back and the initial 90-day sync will begin
4. Connect to Claude
- Go to Claude.ai settings → Connectors
- Click "Add custom connector"
- Enter:
- Name: Whoop
- Remote MCP server URL:
https://your-app.railway.app/mcp
- Use it in any chat!
Local Development
# Install dependencies
npm install
# Create .env file
cat > .env << EOF
WHOOP_CLIENT_ID=your_client_id
WHOOP_CLIENT_SECRET=your_client_secret
WHOOP_REDIRECT_URI=http://localhost:3000/callback
MCP_MODE=http
EOF
# Run in development mode
npm run dev
Environment Variables
| Variable | Description | Default |
|---|---|---|
WHOOP_CLIENT_ID |
Whoop OAuth client ID | Required |
WHOOP_CLIENT_SECRET |
Whoop OAuth client secret | Required |
WHOOP_REDIRECT_URI |
OAuth callback URL | http://localhost:3000/callback |
DB_PATH |
SQLite database path | ./whoop.db |
PORT |
HTTP server port | 3000 |
MCP_MODE |
http for remote, stdio for local |
http |
Architecture
┌─────────────────────────────────────────────────┐
│ Whoop MCP Server │
│ │
│ ┌─────────────┐ ┌──────────────────┐ │
│ │ MCP Server │◄────►│ SQLite Database │ │
│ │ (HTTP) │ │ - cycles │ │
│ └─────────────┘ │ - recovery │ │
│ │ │ - sleep │ │
│ │ │ - workouts │ │
│ ▼ │ - tokens │ │
│ ┌─────────────┐ └──────────────────┘ │
│ │ Whoop API │ │
│ │ Client │ │
│ └─────────────┘ │
└─────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────┐
│ Claude.ai (Custom Connector) │
│ "Hey, what's my recovery today?" │
└─────────────────────────────────────────────────┘
API Endpoints Used
This server uses the following Whoop API v2 endpoints:
GET /v2/user/profile/basic- User profileGET /v2/user/measurement/body- Body measurementsGET /v2/cycle- Physiological cycles (strain data)GET /v2/recovery- Recovery scoresGET /v2/activity/sleep- Sleep recordsGET /v2/activity/workout- Workout records
License
MIT - See LICENSE for details.
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。