Bring Apple Health history into an AI workflow with MCP

Description and use

Apple Health AI Bridge connects Apple Health data to AI clients via a local MCP server, simplifying historical data queries without manual export.

Problem

Access Apple Health data in AI tools without manual export and re‑archive for each query.

Outcome

The bridge allows AI clients to query Apple Health history directly, supporting period comparisons, metric selection, and time‑series analysis without manual data export.

Workflow

• 1. Install the Apple Health AI Bridge companion on an iPhone (iOS 18+).
• 2. Pair the iPhone with a Mac or Linux receiver following the install guide.
• 3. The receiver stores incoming data in a local SQLite database and generates a local stdio MCP descriptor.
• 4. Configure an AI client to use the MCP descriptor to connect to the receiver.
• 5. Use MCP tools such as get_daily_summary, get_sleep_summary, get_workouts, get_timeseries, list_synced_metrics, list_supported_timeseries_types, and explain_sources to query historical data.
• 6. The AI client can ask questions like “Compare my recorded activity in October 1‑7 with September 24‑30” and receive structured responses without re‑exporting data.

Evidence

Apple Health AI Bridge, a free, open‑source project that makes Apple Health records available to AI tools and scripts.

Source

The receiver stores the history in SQLite and exposes a CLI and local read‑only MCP server.

Source

You can compare two periods, choose a different metric, or revisit the comparison after more records arrive, without preparing another archive for each conversation.

Source

The client can request the periods through get_daily_summary, then use get_sleep_summary and get_workouts for the relevant records.

Source

Setup generates a local stdio MCP descriptor with the executable command and database arguments.

Source