whoop-mcp
MCP server that connects Whoop fitness data to Claude, enabling natural language queries about recovery, sleep, workouts, and more.
README
whoop-mcp
A Model Context Protocol (MCP) server that connects your Whoop fitness data to Claude. Ask natural language questions about your recovery, sleep, workouts, and more — directly in Claude chat.
What You Can Ask
- "What was my recovery score today?"
- "How did I sleep this week?"
- "Show me my HRV trend over the last 30 days"
- "Which workouts had the highest strain?"
- "Compare my sleep efficiency this month"
Available Tools
| Tool | Description |
|---|---|
get_profile |
Your name and email |
get_body_measurement |
Height, weight, max heart rate |
get_recovery |
Recovery %, HRV, resting heart rate, SpO2 |
get_sleep |
Duration, efficiency, sleep stages, disturbances |
get_workouts |
Strain, calories, sport type |
get_cycles |
Daily strain and total calories burned |
All data tools accept optional start and end date parameters and default to the last 30 days.
Setup
1. Prerequisites
Install uv:
curl -LsSf https://astral.sh/uv/install.sh | sh
Clone this repo to a path without spaces:
git clone https://github.com/your-username/whoop-mcp.git ~/whoop-mcp
cd ~/whoop-mcp
Install dependencies:
uv venv --python 3.12
uv pip install mcp httpx
2. Get Whoop API credentials
- Go to https://developer.whoop.com/
- Create a new app and fill in:
- Redirect URI:
http://localhost:8888/callback - Privacy Policy URL: your GitHub Pages URL (see Privacy Policy below)
- Redirect URI:
- Copy your Client ID and Client Secret
3. Authenticate (one time only)
WHOOP_CLIENT_ID=your_client_id \
WHOOP_CLIENT_SECRET=your_client_secret \
.venv/bin/python auth.py
This opens the Whoop authorization page in your browser. After you approve:
- Your browser will show an error on
localhost:8888— that's expected - Copy the full URL from the address bar and paste it into the terminal
- Tokens are saved to
~/.whoop_tokens.json
You will not need to do this again. The server automatically refreshes your token.
4. Configure the Claude Desktop App
Edit ~/Library/Application Support/Claude/claude_desktop_config.json and add:
{
"mcpServers": {
"whoop": {
"command": "/Users/your-username/whoop-mcp/.venv/bin/python",
"args": ["/Users/your-username/whoop-mcp/server.py"],
"env": {
"WHOOP_CLIENT_ID": "your_client_id",
"WHOOP_CLIENT_SECRET": "your_client_secret"
}
}
}
}
Important: The path to
whoop-mcpmust not contain spaces — this is why step 1 clones to~/whoop-mcp.
5. Restart Claude
Fully quit Claude (Cmd+Q) and reopen it. The Whoop server should show as connected under Settings → Developer.
Privacy Policy
privacy.html is a ready-to-host privacy policy page required by the Whoop developer portal.
Host it on GitHub Pages:
- Push this repo to GitHub
- Go to Settings → Pages → Source → Deploy from a branch → main / root
- Your privacy policy URL will be:
https://your-username.github.io/whoop-mcp/privacy.html
Webhooks (optional)
webhook_server.py receives real-time events from Whoop when new data is recorded.
WHOOP_CLIENT_SECRET=your_client_secret .venv/bin/python webhook_server.py
For local development, expose it with ngrok:
ngrok http 8080
# Register the https URL in the Whoop developer portal
Supported events: workout.updated, sleep.updated, recovery.updated, body_measurement.updated
Project Structure
whoop-mcp/
├── server.py # MCP server — tools Claude calls
├── whoop_client.py # Whoop API v2 client with auto token refresh
├── auth.py # One-time OAuth setup script
├── webhook_server.py # Real-time Whoop event receiver (optional)
├── privacy.html # Privacy policy page for GitHub Pages
└── requirements.txt # Python dependencies (mcp, httpx)
Notes
- Tokens are stored at
~/.whoop_tokens.jsonand auto-refreshed — you never need to re-runauth.pyunless you revoke access from the Whoop app - Uses the Whoop API v2
- Tested on macOS with Python 3.12
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.