Hevy MCP Server
by VReippainen
The Hevy MCP Server connects your Hevy workout data to Language Models via the Model Context Protocol (MCP). It fetches data from the Hevy API and provides tools for accessing workout history, exercise progress, and personal records.
Last updated: N/A
What is Hevy MCP Server?
The Hevy MCP Server is a TypeScript Node.js server that acts as a bridge between your Hevy workout data and Language Models (LLMs) using the Model Context Protocol (MCP). It allows AI assistants to access and analyze your workout data, enabling personalized fitness recommendations and insights.
How to use Hevy MCP Server?
To use the server, you need a Hevy API key obtained from the Hevy developer portal. Configure the server with your API key and add it to your AI assistant environment (e.g., Cursor) by updating the appropriate configuration file with the server's command and environment variables. Refer to the documentation for detailed instructions.
Key features of Hevy MCP Server
Fetches workout data from Hevy API
Provides tools for accessing workout history, exercise progress, and personal records
Includes a smart workout prompt builder for personalized recommendations
Offers comprehensive documentation of available tools and parameters
Supports integration with LLMs via Model Context Protocol (MCP)
Use cases of Hevy MCP Server
Personalized workout recommendations from AI assistants
Analysis of workout history and progress
Tracking exercise performance over time
Generating workout prompts based on user data
FAQ from Hevy MCP Server
What is Model Context Protocol (MCP)?
What is Model Context Protocol (MCP)?
MCP is a standard that allows LLMs to integrate with external data sources and tools.
How do I get my Hevy API key?
How do I get my Hevy API key?
Visit the Hevy API Documentation and follow the authentication instructions to sign up for API access through the Hevy developer portal.
What tools are available in the MCP server?
What tools are available in the MCP server?
The server provides tools like get-workouts, get-exercise-progress-by-ids, get-exercises, and get-routines.
Where can I find detailed technical information about the server?
Where can I find detailed technical information about the server?
See the TECHNICAL.md file for information about installation, configuration, API endpoints, and project structure.
How is the project versioned and released?
How is the project versioned and released?
This project uses semantic-release for automated versioning and package publishing, following the Conventional Commits specification for commit messages.