Hevy MCP

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

Prerequisites

• Node.js (v20 or higher)
• npm or yarn
• A Hevy API key

Installation

Installing via Smithery

To install hevy-mcp for Claude Desktop automatically via Smithery:

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

Create a .env file in the project root (you can copy from .env.sample) with the following content:

Replace your_hevy_api_key_here with your actual Hevy API key.

Transport Modes

The MCP server supports two transport modes:

Stdio Transport (Default)

The default mode uses stdio transport, which is suitable for integration with MCP clients like Claude Desktop and Cursor:

HTTP Transport

The server can also run in HTTP mode for remote access or web-based integrations:

HTTP Configuration

The HTTP transport can be configured using environment variables:

HTTP Endpoints

When running in HTTP mode, the following endpoints are available:

• POST /mcp - MCP client-to-server communication
• GET /mcp - Server-to-client notifications (SSE)
• DELETE /mcp - Session termination
• GET /health - Health check endpoint

Session Management

The HTTP transport includes session management for stateful connections. Each client session is identified by a unique session ID that must be included in the mcp-session-id header for subsequent requests.

Usage

Development

This starts the MCP server in development mode with hot reloading.

Production

Available MCP Tools

The server implements the following MCP tools for interacting with the Hevy API:

Workout Tools

• get-workouts: Fetch and format workout data
• get-workout: Get a single workout by ID
• create-workout: Create a new workout
• update-workout: Update an existing workout
• get-workout-count: Get the total count of workouts
• get-workout-events: Get workout update/delete events

Routine Tools

• get-routines: Fetch and format routine data
• create-routine: Create a new routine
• update-routine: Update an existing routine
• get-routine-by-id: Get a single routine by ID using direct endpoint

Exercise Template Tools

• get-exercise-templates: Fetch exercise templates
• get-exercise-template: Get a template by ID

Routine Folder Tools

• get-routine-folders: Fetch routine folders
• create-routine-folder: Create a new folder
• get-routine-folder: Get a folder by ID

Webhook Tools

• get-webhook-subscription: Get the current webhook subscription
• create-webhook-subscription: Create a new webhook subscription
• delete-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_KEY environment 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:

1. Unit tests will always run on every push and pull request
2. Integration tests will only run if the HEVY_API_KEY secret is set in the repository settings

To set up the HEVY_API_KEY secret:

1. Go to your GitHub repository
2. Click on "Settings" > "Secrets and variables" > "Actions"
3. Click on "New repository secret"
4. Set the name to HEVY_API_KEY and the value to your Hevy API key
5. Click "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.

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