The Hevy MCP server enables AI assistants to interact with the Hevy fitness tracking app API for comprehensive fitness data management:
Workout Management: Fetch, create, update, and track workouts with detailed exercise data
Routine Management: Access, create, update, and organize workout routines
Exercise Templates: Browse and retrieve both standard and custom exercise templates
Folder Organization: Create and manage folders to categorize routines effectively
Utilized for code formatting and linting in the development process of the MCP server.
Used for environment variable configuration to store the Hevy API key.
Used for version control of the MCP server codebase.
Hosts the repository for the MCP server codebase.
Provides tools for accessing and managing workout data, routines, exercise templates, and folders through the Hevy fitness app API, enabling workout tracking and fitness management capabilities.
Required as a runtime environment (v20 or higher) for running the MCP server.
Used as a package manager for installing and managing dependencies of the MCP server.
Provides badge for license information in the README.
Supported as an alternative package manager for installing and managing dependencies.
hevy-mcp: Model Context Protocol Server for Hevy Fitness API
A Model Context Protocol (MCP) server implementation that interfaces with the Hevy fitness tracking app and its API. This server enables AI assistants to access and manage workout data, routines, exercise templates, and more through the Hevy API (requires PRO subscription).
Features
Workout Management: Fetch, create, and update workouts
Routine Management: Access and manage workout routines
Exercise Templates: Browse available exercise templates
Folder Organization: Manage routine folders
Webhook Subscriptions: Create, view, and delete webhook subscriptions for workout events
Note: HTTP transport and Docker images remain deprecated. Smithery deployment now uses the official TypeScript runtime flow (no Docker required), or you can run the server locally via stdio (e.g.,
npx hevy-mcp). Existing GHCR images remain available but are no longer updated.
Related MCP server: AgentMode
Prerequisites
Node.js (v20 or higher)
pnpm (via Corepack)
A Hevy API key
Installation
Run via npx (recommended)
You can launch the server directly without cloning:
Manual Installation
Integration with Cursor
To use this MCP server with Cursor, you need to update your ~/.cursor/mcp.json file by adding the following configuration:
Make sure to replace your-api-key-here with your actual Hevy API key.
Configuration
You can supply your Hevy API key in two ways:
Environment variable (
HEVY_API_KEY)Command-line argument (
--hevy-api-key=your_keyorhevy-api-key=your_keyafter--when using pnpm scripts)
Create a .env file in the project root (you can copy from .env.sample) with the following content if using the environment variable approach:
Replace your_hevy_api_key_here with your actual Hevy API key. If you prefer the command argument approach you can skip setting the environment variable and start the server with for example:
Transport
Deploy via Smithery (TypeScript runtime)
Smithery can bundle and host hevy-mcp without Docker by importing the exported createServer and configSchema from src/index.ts.
Ensure dependencies are installed:
pnpm installLaunch the Smithery playground locally:
pnpm run smithery:devThe CLI will prompt for
HEVY_API_KEY, invokecreateServer({ config }), and open the Smithery MCP playground.Build the deployable bundle:
pnpm run smithery:buildConnect the repository to Smithery and trigger a deployment from their dashboard. Configuration is handled entirely through the exported Zod schema, so no additional
smithery.yamlenv mapping is required.
hevy-mcp now runs exclusively over stdio, which works seamlessly with MCP-aware clients like Claude Desktop and Cursor. HTTP transport has been removed to simplify deployment.
Usage
Development
This starts the MCP server in development mode with hot reloading.
Production
Docker (deprecated)
Docker-based workflows have been retired so we can focus on the stdio-native experience. The bundled Dockerfile now exits with a clear message to prevent accidental builds, and .dockerignore simply documents the deprecation. Previously published images remain available on GHCR (for example ghcr.io/chrisdoc/hevy-mcp:latest), but they are no longer updated. For the best experience, run the server locally via npx hevy-mcp or your own Node.js runtime.
Available MCP Tools
The server implements the following MCP tools for interacting with the Hevy API:
Workout Tools
get-workouts: Fetch and format workout dataget-workout: Get a single workout by IDcreate-workout: Create a new workoutupdate-workout: Update an existing workoutget-workout-count: Get the total count of workoutsget-workout-events: Get workout update/delete events
Routine Tools
get-routines: Fetch and format routine datacreate-routine: Create a new routineupdate-routine: Update an existing routineget-routine-by-id: Get a single routine by ID using direct endpoint
Exercise Template Tools
get-exercise-templates: Fetch exercise templatesget-exercise-template: Get a template by ID
Routine Folder Tools
get-routine-folders: Fetch routine folderscreate-routine-folder: Create a new folderget-routine-folder: Get a folder by ID
Webhook Tools
get-webhook-subscription: Get the current webhook subscriptioncreate-webhook-subscription: Create a new webhook subscriptiondelete-webhook-subscription: Delete the current webhook subscription
Project Structure
Development Guide
Code Style
This project uses Biome for code formatting and linting:
Testing
Run All Tests
To run all tests (unit and integration), use:
Note: If the
HEVY_API_KEYenvironment variable is set, integration tests will also run. If not, only unit tests will run.
Run Only Unit Tests
To run only unit tests (excluding integration tests):
Or with coverage:
Run Only Integration Tests
To run only the integration tests (requires a valid HEVY_API_KEY):
Note: The integration tests will fail if the HEVY_API_KEY environment variable is not set. This is by design to ensure that the tests are always run with a valid API key.
GitHub Actions Configuration
For GitHub Actions:
Unit tests will always run on every push and pull request
Integration tests will only run if the
HEVY_API_KEYsecret is set in the repository settings
To set up the HEVY_API_KEY secret:
Go to your GitHub repository
Click on "Settings" > "Secrets and variables" > "Actions"
Click on "New repository secret"
Set the name to
HEVY_API_KEYand the value to your Hevy API keyClick "Add secret"
If the secret is not set, the integration tests step will be skipped with a message indicating that the API key is missing.
Generating API Client
The API client is generated from the OpenAPI specification using Kubb:
Kubb generates TypeScript types, API clients, Zod schemas, and mock data from the OpenAPI specification.
Troubleshooting
Rollup optional dependency missing: If you see an error similar to
Cannot find module @rollup/rollup-linux-x64-gnu, set the environment variableROLLUP_SKIP_NODEJS_NATIVE_BUILD=truebefore runningpnpm run build. This forces Rollup to use the pure JavaScript fallback and avoids the npm optional dependency bug on some Linux runners.
License
This project is licensed under the MIT License - see the LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
Acknowledgements
Model Context Protocol for the MCP SDK
Hevy for their fitness tracking platform and API