Fitbit MCP Connector for AI

Connect AI assistants to your Fitbit health data

Give your AI assistant access to your Fitbit data for personalized health insights, trend analysis, and automated tracking. Works with Claude Desktop and other MCP-compatible AI tools.

What it does

🏃 Exercise & Activities - Get detailed workout logs and activity data
😴 Sleep Analysis - Retrieve sleep patterns and quality metrics
⚖️ Weight Tracking - Access weight trends over time
❤️ Heart Rate Data - Monitor heart rate patterns and zones
🍎 Nutrition Logs - Review food intake, calories, and macros
👤 Profile Info - Access basic Fitbit profile details

Ask your AI things like: "Show me my sleep patterns this week" or "What's my average heart rate during workouts?"

Quick Start

🚀 Want to test the tools right away?

Option 1: Install from npm (Recommended)

1. Get Fitbit API credentials

   • Create an app with OAuth 2.0 Application Type: Personal
   • Set Callback URL: http://localhost:3000/callback
   • Note your Client ID and Client Secret

2. Install the package globally:

npm install -g mcp-fitbit

1. Add to your Claude Desktop config file:

{
  "mcpServers": {
    "fitbit": {
      "command": "mcp-fitbit",
      "args": [],
      "env": {
        "FITBIT_CLIENT_ID": "your_client_id_here",
        "FITBIT_CLIENT_SECRET": "your_client_secret_here"
      }
    }
  }
}

• Config file location:
  • Windows: %AppData%\Claude\claude_desktop_config.json
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

1. Restart Claude Desktop and ask about your Fitbit data!

Option 2: Development Setup

1. Get Fitbit API credentials (see Installation below)
2. Then run:

git clone https://github.com/TheDigitalNinja/mcp-fitbit
cd mcp-fitbit
npm install
# Create .env with your Fitbit credentials
npm run dev

Both options open the MCP Inspector at http://localhost:5173 where you can test all tools interactively and handle the OAuth flow.

Installation

For End Users (npm package)

1. Get Fitbit API credentials at dev.fitbit.com

   • Set OAuth 2.0 Application Type to Personal
   • Set Callback URL to http://localhost:3000/callback

2. Install the package:

   npm install -g mcp-fitbit
   

3. Create .env file in the package directory:

   When you run mcp-fitbit for the first time, it will tell you exactly where to create the .env file. It will look something like:

   C:\Users\YourName\AppData\Roaming\npm\node_modules\mcp-fitbit\.env
   

4. Add your credentials to the .env file:

   FITBIT_CLIENT_ID=your_client_id_here
   FITBIT_CLIENT_SECRET=your_client_secret_here
   

5. Run the server:

   mcp-fitbit
   

For Developers (from source)

1. Get Fitbit API credentials at dev.fitbit.com

   • Set OAuth 2.0 Application Type to Personal
   • Set Callback URL to http://localhost:3000/callback

2. Clone and setup:

   git clone https://github.com/TheDigitalNinja/mcp-fitbit
   cd mcp-fitbit
   npm install
   

3. Create .env file:

   FITBIT_CLIENT_ID=your_client_id_here
   FITBIT_CLIENT_SECRET=your_client_secret_here
   

4. Build the server:

   npm run build
   

Available Tools

Nutrition resources: caloriesIn, water, protein, carbs, fat, fiber, sodium

Activity time series resources: steps, distance, calories, activityCalories, caloriesBMR, tracker/activityCalories, tracker/calories, tracker/distance

Claude Desktop

Using npm package (recommended):

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "fitbit": {
      "command": "mcp-fitbit",
      "args": []
    }
  }
}

Using local development version:

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "fitbit": {
      "command": "node",
      "args": ["C:\\path\\to\\mcp-fitbit\\build\\index.js"]
    }
  }
}

Config file locations:

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

First Run Authorization

When you first ask your AI assistant to use Fitbit data:

1. The server opens your browser to http://localhost:3000/auth
2. Log in to Fitbit and grant permissions
3. You'll be redirected to a success page
4. Your AI can now access your Fitbit data!

Development

npm run lint          # Check code quality
npm run format        # Fix formatting
npm run build         # Compile TypeScript
npm run dev           # Run with MCP inspector

Architecture: See TASKS.md for improvement opportunities and technical details.