Skip to main content

What is MCP?

MCP (Model Context Protocol) is a standard for connecting AI assistants to external data sources. The Open Wearables MCP server enables AI tools like Claude Desktop and Cursor to query your wearable health data through natural language conversations.
The MCP server is decoupled from the backend - it communicates via REST API using your API key. This means it can be deployed independently and uses existing, tested API endpoints.

Demo

This demo uses generated sample data to show the capabilities of Claude’s MCP integration with Open Wearables. User 1 has short, irregular sleep patterns while User 2 shows longer, more consistent sleep quality. Claude analyzes both datasets to identify key differences and health implications.

Available Tools

The MCP server provides the following tools for AI assistants:

List Users

Discover users accessible via your API key. Optionally filter by name or email.

Activity Summary

Get daily activity data including steps, calories, heart rate, and intensity minutes.

Sleep Summary

Get sleep data for a user within a date range.

Workout Events

Get workout and exercise sessions for a user within a date range.

Example Interactions

Discovering users

Querying sleep data

Generic request (no time range specified)

Quick Start

Prerequisites

  • uv package manager
  • Running Open Wearables backend (or access to a deployed instance)
  • Valid Open Wearables API key

1. Install dependencies

2. Configure environment

Edit config/.env with your settings:
To generate your API key, go to the Open Wearables Dashboard -> Settings -> Credentials -> Create API Key.

3. Test the server

If the server starts successfully, you should see output similar to:
You can stop the server now - the LLM client you configure in the next steps will start it automatically on launch.

Next Steps

Claude Desktop Setup

Configure the MCP server with Claude Desktop.

Cursor Setup

Configure the MCP server with Cursor IDE.