Fitbit MCP Server Integration

What does “Fitbit” MCP Server do?

The Fitbit MCP (Model Context Protocol) Server is an integration layer that enables AI assistants to access, analyze, and interact with Fitbit health and fitness data. By connecting external AI models to your Fitbit account, this MCP server allows developers and AI-powered applications to retrieve a wide variety of personal health metrics, including activity logs, heart rate, sleep patterns, nutrition, and device information. This capability empowers applications to deliver personalized insights, automate wellness tracking, and enhance user engagement with data-driven health recommendations. The Fitbit MCP Server streamlines the process of querying Fitbit’s APIs, making it easier for developers to build tools and workflows that incorporate users’ health and fitness context seamlessly into their products.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

No explicit MCP resources are documented in the repository.

List of Tools

• getUserProfile: Retrieve your Fitbit profile information.
• getActivities: Fetch activity data for a specific date.
• getSleepLogs: Access sleep data for a specified date.
• getHeartRate: Obtain heart rate data for a specific date and period.
• getSteps: Get step count for a given date and period.
• getBodyMeasurements: Retrieve weight and body fat measurements.
• getFoodLogs: Access food log data for a specified date.
• getWaterLogs: Fetch water consumption data for a specified date.
• getLifetimeStats: Retrieve lifetime activity statistics.
• getUserSettings: Access user settings and preferences.
• getFloorsClimbed: Get data on floors climbed.
• getDistance: Retrieve distance data for a specified date.
• getCalories: Get calories burned data.
• getActiveZoneMinutes: Access active zone minutes data.
• getDevices: Get information about connected Fitbit devices.
• getBadges: Retrieve earned badges and achievements.

Use Cases of this MCP Server

• Personal Health Dashboards: Aggregate and display personalized health and fitness data (activity, sleep, heart rate) in dashboards for users, enabling deeper self-monitoring and progress tracking.
• Wellness Recommendations: Enable AI assistants to provide context-aware health and fitness advice based on real Fitbit data, such as encouraging more steps or improved sleep.
• Automated Fitness Tracking: Integrate Fitbit data into broader wellness platforms, automating the collection and analysis of users’ activity and health metrics.
• Longitudinal Health Analysis: Allow developers to pull and analyze historical health data for trend analysis or research purposes.
• Device Monitoring and Management: Provide insights and status reports on connected Fitbit devices for troubleshooting or usage optimization.

How to set it up

Windsurf

1. Ensure Node.js is installed on your system.
2. Obtain your Fitbit access token by registering an app on the Fitbit Developer Portal.
3. Open your Windsurf configuration file.
4. Add the Fitbit MCP Server using the following JSON snippet:

   {
     "mcpServers": {
       "fitbit-mcp": {
         "command": "npx",
         "args": ["-y", "fitbit-mcp", "--stdio"],
         "env": {
           "FITBIT_ACCESS_TOKEN": "YOUR_FITBIT_ACCESS_TOKEN"
         }
       }
     }
   }
   

5. Save the file and restart Windsurf to apply changes.

Securing API Keys:
Store your Fitbit access token in an environment variable to avoid exposing it in configuration files:

{
  "env": {
    "FITBIT_ACCESS_TOKEN": "${FITBIT_ACCESS_TOKEN}"
  }
}

Claude

1. Install Node.js and obtain a Fitbit access token as above.
2. Locate the Claude configuration file.
3. Insert the following configuration under MCP servers:

   {
     "mcpServers": {
       "fitbit-mcp": {
         "command": "npx",
         "args": ["-y", "fitbit-mcp", "--stdio"],
         "env": {
           "FITBIT_ACCESS_TOKEN": "YOUR_FITBIT_ACCESS_TOKEN"
         }
       }
     }
   }
   

4. Save and restart Claude.
5. Verify with a test query to Fitbit data.

Securing API Keys:

{
  "env": {
    "FITBIT_ACCESS_TOKEN": "${FITBIT_ACCESS_TOKEN}"
  }
}

Cursor

1. Install Node.js and get a Fitbit access token.
2. Open Cursor’s configuration file.
3. Add the Fitbit MCP Server:

   {
     "mcpServers": {
       "fitbit-mcp": {
         "command": "npx",
         "args": ["-y", "fitbit-mcp", "--stdio"],
         "env": {
           "FITBIT_ACCESS_TOKEN": "YOUR_FITBIT_ACCESS_TOKEN"
         }
       }
     }
   }
   

4. Save and restart Cursor.
5. Confirm integration by running a Fitbit data request.

Securing API Keys:

{
  "env": {
    "FITBIT_ACCESS_TOKEN": "${FITBIT_ACCESS_TOKEN}"
  }
}

Cline

1. Make sure Node.js is installed and a Fitbit access token is available.
2. Open your Cline configuration.
3. Add the MCP server entry:

   {
     "mcpServers": {
       "fitbit-mcp": {
         "command": "npx",
         "args": ["-y", "fitbit-mcp", "--stdio"],
         "env": {
           "FITBIT_ACCESS_TOKEN": "YOUR_FITBIT_ACCESS_TOKEN"
         }
       }
     }
   }
   

4. Save and restart Cline.
5. Test the setup with an AI assistant health query.

Securing API Keys:

{
  "env": {
    "FITBIT_ACCESS_TOKEN": "${FITBIT_ACCESS_TOKEN}"
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "fitbit-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “fitbit-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between the two tables, the Fitbit MCP server is well-documented for tools and setup. However, lack of prompt and resource definitions, and no explicit mention of sampling or roots, slightly limits its completeness for full MCP ecosystem integration. Based on this, I would rate this MCP server a 6/10 for its practical utility and clarity, but with room for improvement in MCP-native features.

MCP Score