whoop-tracker-mcp-server
Integrates with Whoop API v2 to access user profile, sleep, recovery, cycles, and workout data via natural language, with OAuth2 authentication and automatic token refresh.
README
Whoop MCP Server
A lightweight MCP (Model Context Protocol) server for integrating with the Whoop API v2. Built for use with Claude Desktop and other MCP clients.
Features
- 🔐 OAuth 2.0 authentication with Whoop
- 🔄 Automatic token refresh
- 📊 Access to all major Whoop data endpoints:
- User profile and body measurements
- Sleep, recovery, and cycle data
- Workout information
- 🐳 Docker support for easy deployment
- 💾 Persistent token storage
Quick Start
Prerequisites
- Node.js >= 22.0.0 (for Method 1) OR Docker (for Method 2)
- pnpm >= 10.0.0 (for Method 1 only)
- Whoop Developer Account
Setup for Claude Desktop
Choose one of the two methods below to integrate with Claude Desktop. The MCP server runs as part of Claude Desktop - you don't need to start it separately.
Method 1: Using Node.js
-
Clone and install:
git clone https://github.com/alacore/whoop-tracker-mcp-server.git cd whoop-tracker-mcp-server pnpm install -
Build the server:
pnpm run build -
Configure Claude Desktop - see Claude Desktop Configuration section below
Method 2: Using Docker
-
Clone the repository:
git clone https://github.com/alacore/whoop-tracker-mcp-server.git cd whoop-tracker-mcp-server -
Build Docker image:
docker build -t whoop-mcp . -
Configure Claude Desktop - see Claude Desktop Configuration section below
Development Mode (Optional)
For testing the MCP server independently or during development:
-
Configure environment:
cp .env.example .envEdit
.envwith your Whoop OAuth credentials:WHOOP_CLIENT_ID=your_whoop_client_id WHOOP_CLIENT_SECRET=your_whoop_client_secret WHOOP_REDIRECT_URI=http://localhost:3000/callback WHOOP_SCOPES=offline read:profile read:body_measurement read:cycles read:recovery read:sleep read:workout -
Run in development mode:
pnpm run devNote: This runs the server standalone for testing. For actual use with Claude Desktop, follow the configuration instructions below.
Usage
Claude Desktop Configuration
Method 1: Direct Node.js Execution
Add to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"whoop": {
"command": "node",
"args": ["/path/to/whoop-tracker-mcp-server/dist/mcp-standalone.js"],
"env": {
"WHOOP_CLIENT_ID": "your_client_id",
"WHOOP_CLIENT_SECRET": "your_client_secret",
"WHOOP_REDIRECT_URI": "http://localhost:3000/callback",
"WHOOP_SCOPES": "offline read:profile read:body_measurement read:cycles read:recovery read:sleep read:workout"
}
}
}
}
Prerequisites:
- Node.js >= 22.0.0 installed
- Built server (
pnpm run build) - Replace
/path/to/whoop-tracker-mcp-serverwith your actual project path
Note: The offline scope in WHOOP_SCOPES is required to receive a refresh token during the OAuth2 flow, enabling automatic token renewal without re-authentication.
Method 2: Docker Container
First, build the Docker image:
# Build the Docker image
docker build -t whoop-mcp .
Then add to your Claude Desktop configuration:
{
"mcpServers": {
"whoop": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e",
"WHOOP_CLIENT_ID=your_client_id",
"-e",
"WHOOP_CLIENT_SECRET=your_client_secret",
"-e",
"WHOOP_REDIRECT_URI=http://localhost:3000/callback",
"-e",
"WHOOP_SCOPES=offline read:profile read:body_measurement read:cycles read:recovery read:sleep read:workout",
"-v",
"${HOME}/.whoop-mcp:/home/node/.whoop-mcp",
"whoop-mcp"
]
}
}
}
Prerequisites:
- Docker installed and running
- Built Docker image (
docker build -t whoop-mcp .)
Notes:
- The
-vflag mounts a local directory for persistent token storage across container restarts. First create the directory on your host machine (e.g.,mkdir -p ~/.whoop-mcp), then mount it using the-vflag - this is where auth tokens will be stored - The
offlinescope inWHOOP_SCOPESis required to receive a refresh token during the OAuth2 flow, enabling automatic token renewal without re-authentication
Testing Your Setup
To test either configuration:
- Restart Claude Desktop after updating the configuration
- In Claude, use the Whoop tools:
- Start with
whoop_auth_urlto begin authentication - Follow the OAuth flow to authorize
- Use other tools like
whoop_get_profileto verify access
- Start with
Available MCP Tools
Authentication
- whoop_auth_url - Generate OAuth authorization URL
- whoop_exchange_token - Exchange auth code for access token
- whoop_refresh_token - Refresh expired access token
Data Access
- whoop_get_profile - Get user profile
- whoop_get_body_measurement - Get body measurements
- whoop_get_cycles - Get physiological cycles
- whoop_get_recovery - Get recovery data
- whoop_get_sleep - Get sleep data
- whoop_get_workouts - Get workout data
Authentication Flow
- Use
whoop_auth_urlto get authorization URL - Open URL in browser and authorize
- Copy the
codeparameter from callback URL - Use
whoop_exchange_tokenwith the code - Tokens are automatically saved and refreshed
Development
# Development with hot reload
pnpm run dev
# Build for production
pnpm run build
# Run built version
pnpm start
License
MIT
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.