WHOOP MCP Server for Poke

Connect your WHOOP fitness data to Poke AI assistant using the Model Context Protocol (MCP).

---

🎯 What This Does

This MCP server lets you query your WHOOP fitness data through Poke AI assistant using natural language:

• “What’s my recovery score today?” - Get your daily recovery metrics
• “How did I sleep last night?” - Analyze your sleep performance
• “Show me my strain data” - View workout strain and heart rate zones
• “What’s my biological age?” - Check your WHOOP Age and healthspan metrics

---

✨ Features

• 🏃 5 WHOOP Data Tools: Overview, Sleep, Recovery, Strain, Healthspan
• 🔄 Automatic Token Refresh: Handles authentication seamlessly
• 🌐 Cloud Ready: Deploy to Render with one click
• 🤖 Poke Compatible: Works out of the box with Poke AI

🔑 What Makes This Different

This is a reverse-engineered implementation that directly interfaces with WHOOP’s private API. No official SDK, no OAuth flows, no waiting for API approval. Perfect for developers who don’t want to go through the hassle of WHOOP’s official development program but still want programmatic access to their comprehensive fitness data.

---

🚀 Quick Start

Prerequisites

• Python 3.10 or higher
• WHOOP account with active subscription
• Poke account (for AI assistant integration)
• Render account (free tier works)

Option 1: Deploy to Render (Recommended)

1. Click the “Deploy to Render” button above

2. Configure your deployment:

   • Name: whoop-mcp-server (or your choice)
   • Branch: main

3. Set environment variables:

   • WHOOP_EMAIL: Your WHOOP account email
   • WHOOP_PASSWORD: Your WHOOP account password

4. Wait for deployment (~5-10 minutes)

5. Get your MCP URL:

   https://your-service-name.onrender.com/mcp
   

6. Connect to Poke:

   • Go to https://poke.com/settings/connections/integrations/new
   • Add your MCP URL
   • Start asking questions!

Option 2: Run Locally

1. Clone the repository:

   git clone https://github.com/kabirrgrover/whoop-mcp-poke.git
   cd whoop-mcp-poke
   

2. Create virtual environment:

   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
   

3. Install dependencies:

   pip install -r requirements.txt
   

4. Configure environment:

   cp .env.example .env
   # Edit .env with your WHOOP credentials
   

5. Run the server:

   python src/server.py
   

6. Server runs at: http://localhost:8000/mcp

---

🔧 Configuration

Environment Variables