Apple Health MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CACHE_SIZE | No | Number of cached query results | 100 |
| MAX_MEMORY_MB | No | Maximum memory usage in MB | 1024 |
| HEALTH_DATA_DIR | Yes | Path to your Apple Health CSV export directory |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| health_queryA | Execute SQL queries on Apple Health data. Supports SELECT queries only. |
| health_reportB | Generate structured health reports for a specific period |
| health_schemaA | Get information about available health data tables, their structure, and sample data to help write SQL queries |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| weekly_summary | Summarize the most recent week of health data: activity, heart rate, sleep, and workouts |
| sleep_analysis | Analyze sleep duration, stages, and consistency over a recent period |
| workout_progress | Review workout frequency, duration, and trends over a recent period |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Health data schema | Tables, columns, units, sample rows, and query tips for the loaded export |
| Available tables | Every queryable table in the export with its load state and row count |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: querying data via SQL, generating reports, and inspecting schema. There is no overlap or ambiguity in their roles.
All tool names follow a consistent health_ prefix pattern, making them predictable and easy to navigate. The suffixes (query, report, schema) are clear and uniform.
Three tools is a well-scoped size for a read-only health data server. Each tool serves a core function without redundancy or bloat.
The tool set covers the full read-only lifecycle: explore schema, query raw data, and generate structured reports. No obvious gaps exist for typical health data access needs.