
Whoop MCP
from cbellbell-spin
Local MCP server that exposes Whoop recovery, sleep, and strain data to AI agents
Whoop MCP Server
MCP server that exposes your Whoop fitness data (recovery, sleep, strain, workouts) to Claude for use as a daily training coach.
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_keyโ Fernet encryption key (chmod 600)tokens.encโ Encrypted OAuth tokens (chmod 600)- Directory permissions: chmod 700
If token refresh fails, re-run python scripts/setup_auth.py.
cd whoop-mcp
pip install -r requirements.txtBefore it works, you'll need: WHOOP_CLIENT_IDWHOOP_CLIENT_SECRET
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.txtAuthorization (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.pyThis 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.
No common issues documented yet. If you hit a problem, the repository's GitHub Issues page is the best place to look.
Licensed under MITโ you can use, modify, and redistribute it under that license's terms.
View the full license file on GitHub โ