Hevy MCP

Name: Hevy MCP
Author: amilz

@amilz

リポジトリ

Hevy MCP について

A TypeScript MCP Server for interacting with Hevy Workout App in LLMs

#hevy-mcp #workout-tracking #fitness-assistant

基本情報

カテゴリ

その他

ランタイム

node

トランスポート

stdio

公開者

amilz

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "hevy": {
      "command": "node",
      "args": [
        "/path/to/hevy-mcp/build/src/index.js"
      ],
      "env": {
        "HEVY_API_KEY": ""
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Hevy MCP?

Hevy MCP is a TypeScript-based Model Context Protocol (MCP) server that connects AI assistants to the Hevy workout tracking API. It enables AI tools to retrieve and analyze your workout history, helping you gain insights into your fitness journey.

How to use Hevy MCP?

Clone the repository, install dependencies (npm install), and build the TypeScript code (npm run build). Configure your Hevy API key in your LLM’s MCP settings (e.g., Claude Desktop’s claude_desktop_config.json), restart the LLM, and then ask queries like “Summarize my last 5 workouts.”

Key features of Hevy MCP

Retrieves user workout history from the Hevy API
Implements the Model Context Protocol for AI assistant integration
Simple setup with configurable options
Provides the getWorkouts tool with pagination support

Use cases of Hevy MCP

Ask an AI assistant to summarize your last several workouts
Get recommendations for today’s workout based on recent training data
Analyze workout patterns or progress over time

FAQ from Hevy MCP

What does Hevy MCP do that alternatives don’t?

The README does not compare this server to alternatives. It focuses on integrating Hevy workout data with any MCP‑compatible AI assistant.

What are the runtime requirements?

Node.js v18 or higher, a Hevy API key (obtainable from Hevy Settings), and an LLM that supports the Model Context Protocol (e.g., Claude Desktop).

Where does my workout data live?

Workout data is stored on Hevy’s servers. This server retrieves it from the Hevy API; it does not store data locally or transmit it elsewhere beyond your AI assistant.

Are there any known limitations?

Currently, the server only provides a single tool (getWorkouts with pagination). The author notes that additional methods may not be useful with an LLM and invites ideas via issues or PRs.

How is authentication handled?

Authentication uses a Hevy API key supplied as an environment variable (HEVY_API_KEY) in the LLM’s MCP configuration. No other transport or auth mechanisms are documented.