🏃 Runalyze MCP Server

Access your Runalyze health metrics through AI assistants using the Model Context Protocol (MCP)

A secure MCP server that lets you retrieve health data (HRV, Sleep, Resting Heart Rate, Activities) from your Runalyze account directly within AI chat applications like Claude Desktop and ChatGPT Desktop.

🎯 Choose Your Setup

This server can be used in two ways. Choose the option that works best for you:

Security Note: Both options are secure. The hosted version does NOT store your API token - you provide it with each request, just like the local version stores it in your config file.

📖 Table of Contents

• Option 1: Local Setup
  • Prerequisites
  • Installation
  • Configure Your AI Tool
• Option 2: Hosted Setup
  • Configure Your AI Tool
• What You Can Do
• Troubleshooting

🖥️ Option 1: Local Setup

Run the MCP server on your own computer.

Prerequisites

Before you start, make sure you have:

• Node.js v18 or higher (via Devbox or manual install)
• Yarn package manager (Installation guide)
• A Runalyze account with premium access (Get premium)
• An AI assistant that supports MCP (Claude Desktop, ChatGPT Desktop, VS Code extensions, etc.)

Installation

Step 1: Download and Build

# Clone the repository
git clone https://github.com/floriankimmel/runalyze-mcp-server.git
cd runalyze-mcp-server

Option A: Using Devbox (Recommended)

Devbox provides isolated, reproducible dev environments.

1. Install devbox and direnv:

   # macOS
   brew install devbox direnv
   

2. Enable direnv in the project:

   direnv allow
   

3. Run devbox scripts:

   devbox run install  # yarn install
   devbox run build    # yarn build
   devbox run dev      # yarn start:dev
   devbox run dev:http # yarn start:http:dev
   

Option B: Manual Setup

# Install dependencies
yarn install

# Build the server
yarn build

The compiled server will be in the dist/ directory.

Step 2: Get Your Runalyze API Token

1. Log in to your Runalyze account
2. Go to Settings → Personal API: https://runalyze.com/settings/personal-api
3. Click Generate new token
4. Copy the token (you'll need it in the next step)

Configure Your AI Tool (Local)

Choose your AI assistant and follow the configuration steps:

For Claude Desktop 🟣

1. Locate your configuration file:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json
   • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add the server configuration:

{
  "mcpServers": {
    "run

... [View full README on GitHub](https://github.com/floriankimmel/runalyze-mcp-server#readme)