hevy
Manage your Hevy workouts, routines, folders, and exercise templates. Create and update sessions faster, organize plans, and search exercises to build workouts quickly. Stay synced with changes so your training log is always up to date.
claude mcp add --transport stdio chrisdoc-hevy-mcp npx -y hevy-mcp \ --env HEVY_API_KEY="your-api-key-here"
How to use
hevy-mcp is a Model Context Protocol server that integrates with the Hevy Fitness API. It exposes a set of MCP tools to manage workouts, routines, and exercise templates by leveraging the Hevy API (requires a PRO subscription). The server operates via stdio transport, meaning it communicates over standard input/output using JSON-RPC messages, which makes it suitable for MCP-aware clients like Claude Desktop and Cursor. You can start the server with npx hevy-mcp (or install locally and run via your preferred Node runtime) and provide your Hevy API key either through the HEVY_API_KEY environment variable or via command-line arguments. The server supports features such as fetching, creating, and updating workouts; managing routines and folders; browsing exercise templates; and handling webhook subscriptions for workout events.
How to install
Prerequisites:
- Node.js v20 or higher
- pnpm (via Corepack)
- A Hevy API key
Installation steps:
- Quick start (run via npx, recommended):
HEVY_API_KEY=your_hevy_api_key_here npx -y hevy-mcp
- Manual installation (clone and install):
# Clone the repository
git clone https://github.com/chrisdoc/hevy-mcp.git
cd hevy-mcp
# Install dependencies (via Corepack pnpm)
corepack use pnpm@10.22.0
pnpm install
# Create environment config
cp .env.sample .env
# Edit .env and add your HEVY_API_KEY
- Cursor integration (example for ~/.cursor/mcp.json):
{
"hevy-mcp": {
"command": "npx",
"args": ["-y", "hevy-mcp"],
"env": {
"HEVY_API_KEY": "your-api-key-here"
}
}
}
- If you need to migrate from HTTP/SSE transport, update client config to use stdio transport as shown above.
Additional notes
Notes and tips:
- Transport: As of v1.18.0, hevy-mcp uses stdio transport only. HTTP/SSE transport is deprecated and removed; ensure clients are configured for stdio.
- Sentry: The published MCP server includes Sentry monitoring. There is no built-in toggle to disable Sentry in the published package; to remove telemetry, fork and remove Sentry initialization in src/index.ts.
- Production vs development: Use pnpm run dev for development with hot reloading, or pnpm run build followed by pnpm start for production.
- Docker: Docker-based deployment is deprecated; running locally with npx hevy-mcp or your Node runtime is recommended.
- Environment variables: Provide HEVY_API_KEY securely via environment variables or via command-line arguments (e.g., --hevy-api-key=...).
- API scope: The server requires a PRO subscription to access Hevy API data such as workouts, routines, templates, and webhook events.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
promptboard
The Shared Whiteboard for Your AI Agents via MCP. Paste screenshots, mark them up, and share with AI.