#3 · Primary category: AI Health & Fitness Tracking

apple-health-mcp

apple-health claude duckdb health-data mcp mcp-server model-context-protocol quantified-self sql

Local-first Apple Health MCP server. Lets AI assistants answer questions about your sleep, workouts, activity and heart data from a local export.

Project last updated:08/27/26

GitHub Stars

564

Forks

22

Contributors

1

License

MIT

Why we included this project

Apple Health quietly accumulates years of sleep, workout, and heart data on your iPhone, but getting an AI assistant to actually use it usually means wrestling with exports. This server runs locally and reads a CSV export through DuckDB, so you can ask an MCP client fairly specific questions about trends or ranges instead of settling for canned answers. It exposes three tools: schema discovery, read-only SQL queries, and periodic summaries. The local-first design is the real selling point for health data, since the export never leaves your machine and the server makes no network requests beyond what your chosen model provider already sees. Quantified-self users and developers who want a scriptable layer over personal records will find it useful, though you do need to create the export with the Simple Health Export CSV app first and trust whichever MCP client you connect it to.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category