WHOOP
MCP server for WHOOP — recovery, strain, sleep, and HRV data for AI agents via Model Context Protocol. Built for self-quantified humans.
What is WHOOP?
WHOOP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for whoop — recovery, strain, sleep, and hrv data for ai agents via model context protocol. built for self-quantified humans.
MCP server for WHOOP — recovery, strain, sleep, and HRV data for AI agents via Model Context Protocol. Built for self-quantified humans.
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP server for WHOOP — recovery, strain, sleep, and HRV data
Use Cases
Maintainer
Works with
Installation
NPM
npx -y whoopManual Installation
npx -y whoopConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use WHOOP
The WHOOP MCP server connects AI assistants to the WHOOP API v2, exposing personal health and fitness data including recovery scores, HRV, sleep analysis, workout strain, and daily cycle metrics. Built for self-quantified athletes and health enthusiasts, it lets users query and analyze their biometric data through natural language conversation. OAuth 2.0 authentication is handled automatically with tokens stored locally, so once set up you can ask questions like 'What was my HRV trend last week?' directly in your AI client.
Prerequisites
- A WHOOP device and active WHOOP membership
- WHOOP Developer account with a registered OAuth application at https://developer.whoop.com/
- WHOOP_CLIENT_ID and WHOOP_CLIENT_SECRET from your developer application
- Python with uv package manager installed, or Node.js for the npx approach
- An MCP-compatible client such as Claude Desktop
Register a WHOOP developer application
Go to https://developer.whoop.com/, create an account, and register a new OAuth application to get your Client ID and Client Secret. Set the redirect URI to http://localhost:8080/callback or as instructed in the repository.
Install the server dependencies
Install the required Python packages using uv or pip.
uv pip install mcp httpxConfigure your MCP client
Add the WHOOP MCP server to your claude_desktop_config.json with your WHOOP OAuth credentials as environment variables.
{
"mcpServers": {
"whoop": {
"command": "npx",
"args": ["-y", "whoop"],
"env": {
"WHOOP_CLIENT_ID": "your_whoop_client_id",
"WHOOP_CLIENT_SECRET": "your_whoop_client_secret"
}
}
}
}Authenticate with WHOOP
On first use, the server will initiate an OAuth 2.0 flow. Follow the authorization URL provided, grant access to your WHOOP data, and the tokens will be saved automatically to ~/.whoop_tokens.json for future sessions.
Query your health data
Ask your AI assistant about your recovery, sleep, or workout data. All tools support optional start and end date parameters and default to the previous 30 days of data.
WHOOP Examples
Client configuration
Claude Desktop configuration for the WHOOP MCP server with OAuth credentials.
{
"mcpServers": {
"whoop": {
"command": "npx",
"args": ["-y", "whoop"],
"env": {
"WHOOP_CLIENT_ID": "your_whoop_client_id",
"WHOOP_CLIENT_SECRET": "your_whoop_client_secret"
}
}
}
}Prompts to try
Example prompts for querying your WHOOP health data through the MCP server.
- "What was my recovery score today?"
- "Show me my HRV trend over the last 30 days"
- "Which workouts last week had the highest strain?"
- "How many hours of deep sleep did I average this month?"
- "What is my resting heart rate trend for the past two weeks?"Troubleshooting WHOOP
OAuth authentication flow does not complete or redirects to an error
Ensure the redirect URI registered in your WHOOP developer application exactly matches the one the server uses (http://localhost:8080/callback). Check that no firewall or VPN is blocking the local callback port.
Token refresh errors: stale or invalid tokens
Delete the ~/.whoop_tokens.json file and restart the server to trigger a fresh OAuth flow. Tokens can expire if the application's client secret has been rotated in the WHOOP developer portal.
WHOOP_CLIENT_ID or WHOOP_CLIENT_SECRET not recognized
Verify the environment variable names are exactly WHOOP_CLIENT_ID and WHOOP_CLIENT_SECRET in your MCP configuration. Ensure there are no extra spaces or quotes in the values.
Frequently Asked Questions about WHOOP
What is WHOOP?
WHOOP is a Model Context Protocol (MCP) server that mcp server for whoop — recovery, strain, sleep, and hrv data for ai agents via model context protocol. built for self-quantified humans. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install WHOOP?
Install via npm with the command: npx -y whoop. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with WHOOP?
WHOOP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is WHOOP free to use?
Yes, WHOOP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
WHOOP Alternatives — Similar Analytics Servers
Looking for alternatives to WHOOP? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.
OpenMetadata
★ 14.0kOpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.
Superset
★ 10.9kAn MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.
Horizon
★ 4.4k📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达
MCP Server Chart
★ 4.1kEnables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations
Muapi CLI
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien
Browse More Analytics MCP Servers
Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up WHOOP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use WHOOP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.