Whoop MCP Server
Exposes Whoop fitness data (recovery, sleep, strain, workouts) to Claude for use as a daily training coach, enabling natural language queries about your health metrics and training readiness.
README
Whoop MCP Server
MCP server that exposes your Whoop fitness data (recovery, sleep, strain, workouts) to Claude for use as a daily training coach.
Prerequisites
- Python 3.10+
- A Whoop Developer account with a registered application
- Your Whoop app's Client ID and Client Secret
Whoop Developer Dashboard Setup
- Go to developer.whoop.com and sign in
- Create a new application
- Set the Redirect URI to:
http://localhost:8080/callback - Enable these scopes:
read:recovery,read:cycles,read:sleep,read:profile,read:body_measurement- Note:
read:workoutandofflinemay not be available on all developer apps. The server handles missing scopes gracefully.
- Note:
- Note your Client ID and Client Secret
Installation
cd whoop-mcp
pip install -r requirements.txt
Authorization (One-Time Setup)
Export your app credentials and run the setup script:
export WHOOP_CLIENT_ID="your-client-id"
export WHOOP_CLIENT_SECRET="your-client-secret"
python scripts/setup_auth.py
This opens a browser to Whoop's authorization page. After you approve, tokens are encrypted and stored at ~/.whoop_mcp/. If the offline scope was granted, tokens refresh automatically. Otherwise, re-run this script when the token expires.
Claude Desktop / Cowork MCP Config
Add this to your Claude MCP configuration:
{
"mcpServers": {
"whoop": {
"command": "python",
"args": ["/absolute/path/to/whoop-mcp/src/whoop_server.py"],
"env": {
"WHOOP_CLIENT_ID": "your-client-id",
"WHOOP_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Replace /absolute/path/to/whoop-mcp with the actual path on your machine.
Available Tools
| Tool | Description |
|---|---|
whoop_check_auth |
Verify tokens are valid and not expired |
whoop_get_latest_recovery |
Most recent recovery score, HRV, resting HR, SpO2 |
whoop_get_recovery_range |
Recovery data for a date range |
whoop_get_latest_sleep |
Last sleep session with stage breakdown |
whoop_get_sleep_range |
Sleep data for a date range |
whoop_get_latest_strain |
Current cycle strain, avg/max HR, kilojoules |
whoop_get_strain_range |
Strain over past N days with average |
whoop_get_workouts |
Workouts with sport ID, strain, HR zones |
whoop_get_profile |
User profile and body measurements |
whoop_get_training_summary |
Aggregated coaching snapshot (start here) |
Example Prompts
Once connected, you can ask Claude things like:
- "What was my recovery yesterday?"
- "How much strain did I accumulate last week?"
- "Am I trending toward overtraining?"
- "How has my HRV changed over the past two weeks?"
- "What were my sleep stages last night?"
- "Compare my strain to my recovery over the past 7 days."
- "Should I do a hard workout today?"
Training Coach Workflow
Start each session by calling whoop_get_training_summary for an overview of recovery status, recent strain load, sleep quality, and a training readiness assessment.
Token Storage
Tokens are stored encrypted at ~/.whoop_mcp/:
.encryption_key— Fernet encryption key (chmod 600)tokens.enc— Encrypted OAuth tokens (chmod 600)- Directory permissions: chmod 700
If token refresh fails, re-run python scripts/setup_auth.py.
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.