WHOOP MCP Server
Enables querying WHOOP biometric data (recovery, strain, sleep, workouts, heart rate) from any MCP-compatible AI client, supporting remote and direct modes.
README
WHOOP MCP Server
MCP server for WHOOP biometric data. Query recovery, strain, sleep, workouts, and heart rate from any MCP-compatible AI client.
Two Modes
- Remote — Calls
/api/whoop/statson a deployed WHOOP-connected site (e.g., patrickwingert.com) - Direct — Talks to the WHOOP API directly with local OAuth + token storage
Both modes expose the same 11 tools through a shared interface.
Setup
1. Build
npm install
npm run build
2. Configure Claude Code
Remote mode (uses an existing WHOOP-connected site):
{
"mcpServers": {
"whoop": {
"command": "node",
"args": ["/path/to/whoop-mcp-server/dist/index.js"],
"env": {
"WHOOP_MODE": "remote",
"WHOOP_BASE_URL": "https://patrickwingert.com"
}
}
}
}
Direct mode (standalone, talks to WHOOP API):
{
"mcpServers": {
"whoop": {
"command": "node",
"args": ["/path/to/whoop-mcp-server/dist/index.js"],
"env": {
"WHOOP_MODE": "direct",
"WHOOP_CLIENT_ID": "your-client-id",
"WHOOP_CLIENT_SECRET": "your-client-secret"
}
}
}
}
3. Direct Mode — WHOOP Developer Setup
- Go to WHOOP Developer Portal
- Create a new application
- Set redirect URI to
http://localhost:8787/callback - Enable scopes:
read:profile,read:recovery,read:cycles,read:workout,read:sleep,read:body_measurement - Copy Client ID and Client Secret to your config
4. Direct Mode — OAuth Flow
On first use, the server will need OAuth tokens. The OAuth flow:
- Server starts a temporary listener on
localhost:8787 - Open the generated authorization URL in your browser
- Authorize on WHOOP's site
- Tokens are stored in
~/.whoop-mcp/tokens.json(chmod 600) - Tokens auto-refresh going forward
Tools
Tier 1 — Biometric Data (read-only)
| Tool | Description |
|---|---|
whoop_get_stats |
Full biometric snapshot (recovery, strain, HR, sleep, workout) |
whoop_get_recovery |
Recovery score (0-100), resting HR, HRV, SpO2, skin temp |
whoop_get_strain |
Daily strain (0-21), kilojoules, average/max HR |
whoop_get_workout |
Latest workout: sport, duration, strain, HR zones, distance |
whoop_get_heart_rate |
Current HR with source context (resting/workout/decay) |
whoop_get_sleep |
Sleep performance, stages, efficiency, respiratory rate |
whoop_get_sleep_need |
Sleep need breakdown: baseline, debt, strain impact, nap offset |
Tier 2 — Diagnostics
| Tool | Description |
|---|---|
whoop_check_health |
Endpoint status, token expiry, connection state |
whoop_get_cache_status |
What's cached, staleness, TTL remaining |
whoop_invalidate_cache |
Force fresh data on next request |
whoop_get_config |
Current mode, target, scopes, cache TTL |
All tools support response_format: markdown (default, human-readable) or json (structured data).
Environment Variables
| Variable | Mode | Required | Description |
|---|---|---|---|
WHOOP_MODE |
Both | Yes | remote or direct |
WHOOP_BASE_URL |
Remote | Yes | Base URL of WHOOP-connected app |
WHOOP_CLIENT_ID |
Direct | Yes | From WHOOP developer dashboard |
WHOOP_CLIENT_SECRET |
Direct | Yes | From WHOOP developer dashboard |
Local Storage (Direct Mode)
~/.whoop-mcp/
├── tokens.json # OAuth tokens (chmod 600)
└── cache.json # Cached API responses
Testing
# Test with MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.js
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.