Skip to main content
Glama
Apple Health Chat MCP

Apple Health Chat MCP

by gh33k
README.md
# Apple Health Chat MCP

Ask Claude natural language questions about your Apple Health data! This MCP server enables conversational analysis of your health metrics from iOS Health Export CSV files.

**Example questions you can ask:**
- "How active was I yesterday?"
- "Did I get enough sleep this week?"
- "What's my step count trend?"
- "Was my heart rate higher than usual today?"

## Quick Start

1. **Install & Build:**
   ```bash
   npm install && npm run build
   ```

2. **Set up your health data:**
   ```bash
   export HEALTH_EXPORT_DIR="/path/to/your/health/export/files"
   ```

3. **Configure Claude Desktop:**
   ```json
   {
     "mcpServers": {
       "apple-health-chat": {
         "command": "node",
         "args": ["/path/to/apple-health-chat-mcp/dist/index.js"],
         "env": {
           "HEALTH_EXPORT_DIR": "/path/to/your/health/files"
         }
       }
     }
   }
   ```

4. **Start asking questions!** Restart Claude Desktop and chat about your health data.

## Features

- **Natural Language Queries**: Ask questions in plain English
- **Comprehensive Metrics**: Steps, heart rate, sleep, energy, and more
- **Flexible Time Periods**: Today, yesterday, last week, custom ranges
- **Local Processing**: CSV files stay on your device
- **Privacy Transparent**: Query results sent to Claude (not raw data)

## Supported Health Metrics

Automatically detects metrics from your Health Export files:
- Step Count, Heart Rate (Min/Max/Avg)
- Sleep Analysis, Active Energy
- And many more from your iOS Health app

## Privacy & Data Flow

**Your CSV files**: Stored and processed locally on your device  
**When you ask Claude**: Query results (like "8,500 steps") are sent to Claude for analysis  
**Raw health data**: Never leaves your device

## Get Your Health Data

1. Use the [iOS Health Export app](https://www.healthyapps.dev/) to export your data
2. Set `HEALTH_EXPORT_DIR` to point to your CSV files
3. Keep personal data out of version control (see `.gitignore`)

## Development

```bash
npm run dev    # Development mode
npm test       # Run tests
npm run lint   # Lint code
```

## License

MIT

## Support

- [Issues](https://github.com/gh33k/apple-health-chat-mcp/issues) - Report bugs or request features
---

**Made with ❤️ for health-conscious people who want to chat with their data**

TDQS

B3.3/5.0

Scored across 6 tools

Disambiguation2/5

Multiple tools have overlapping purposes: health_export_metrics and health_export_get_metrics both retrieve metric data with filtering, and health_export_query can also be used for similar queries. health_export_ask is a catch-all natural language interface that may subsume the others, creating confusion about which tool to select.

Naming Consistency3/5

All tools share the 'health_export_' prefix, but the suffixes mix verb forms (query, report, ask, get_metrics) with noun forms (schema, metrics). The similar names 'health_export_metrics' and 'health_export_get_metrics' further reduce consistency.

Tool Count5/5

With 6 tools, the server is well-scoped for querying and analyzing Apple Health export data. Each tool has a place in the workflow, and the count is within the ideal range for a domain-specific server.

Completeness4/5

The server covers schema discovery, raw data retrieval, aggregated metrics, reports, and natural language queries, providing a solid read-only query surface. Minor gaps exist, such as no explicit way to list all available export files, but these are not critical for the core purpose.

Maintenance

ActivityInactive
ResponsivenessNo recent community issues