HealthKit MCP
Enables AI assistants to access Apple HealthKit workout data by receiving workout information from iOS Shortcuts and serving it through MCP protocol endpoints.
README
HealthKit MCP\n\nTimothy's Apple HealthKit workout integration for Simtheory.ai.\n\n## Overview\n\nThis service receives workout data from iOS Shortcuts and serves it via MCP protocol.\nCaptures: Functional Training, Golf, Yoga, Running, Rowing, Walking, and other workout types.\n\n## Architecture\n\n\niOS Shortcuts (HealthKit) --> POST /ingest/workouts --> HealthKit MCP --> Simtheory.ai\n\n\n1. iOS Shortcut reads HealthKit workouts on your iPhone\n2. Shortcut Automation runs daily (or on-demand)\n3. POSTs data to this service on Railway\n4. MCP endpoints serve workout data to Simtheory.ai\n\n## Endpoints\n\n### Ingest (from iOS Shortcut)\n- POST /ingest/workouts - Receive workouts from iOS Shortcut\n- POST /ingest/workouts/batch - Alternative batch format\n\n### Data (query workouts)\n- GET /data/workouts?days=7 - Get recent workouts\n- GET /data/workouts/today - Get today's workouts\n- GET /data/workouts/date/{date} - Get workouts for specific date\n- GET /data/workouts/type/{type} - Get workouts by type\n- GET /data/workouts/summary?days=7 - Get workout summary\n\n### MCP Protocol (for Simtheory.ai)\n- GET /mcp - Service discovery\n- GET /mcp/tools/get_workouts - Get workouts tool\n- GET /mcp/tools/get_todays_workouts - Get today's workouts tool\n- GET /mcp/tools/get_workout_summary - Get summary tool\n\n## Deployment\n\n### Railway\n\n1. Connect this repo to Railway\n2. Set environment variables:\n - HEALTHKIT_API_KEY - Optional API key for security\n - WORKOUT_STORAGE_PATH - Optional, defaults to /tmp/workouts.json\n3. Deploy!\n\n## iOS Shortcut Setup\n\nSee docs/ios_shortcut.md for instructions on creating the iOS Shortcut.\n\n## Environment Variables\n\n| Variable | Description | Default |\n|----------|-------------|---------|\n| PORT | Server port | 8000 |\n| HEALTHKIT_API_KEY | Optional API key | (none) |\n| WORKOUT_STORAGE_PATH | File storage path | /tmp/workouts.json |\n\n## Supported Workout Types\n\n- Functional Training\n- Golf\n- Yoga\n- Running\n- Rowing\n- Walking\n- Cycling\n- Swimming\n- HIIT\n- Strength Training\n- (any other HealthKit workout type)\n
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.