Apple Health MCP: Query Your Apple Health Data with Natural Language and SQL
This repository profile is provided by osrepos.com, an open source repository discovery platform.

Summary
The `apple-health-mcp` project is an MCP (Model Context Protocol) server designed for querying Apple Health data. It allows users to analyze their health metrics using natural language or direct SQL queries. This server integrates with clients like Claude Desktop, providing powerful tools for health data analysis.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
The apple-health-mcp project by neiltron is an innovative MCP (Model Context Protocol) server that empowers users to interact with their Apple Health data in powerful new ways. Built with TypeScript and leveraging DuckDB for efficient data processing, this server allows you to query your health metrics using either natural language commands or direct SQL queries.
It's important to note that apple-health-mcp currently relies on the Simple Health Export CSV app for exporting your Apple Health data into a usable CSV format. This approach ensures quick and reliable data import for analysis.
Installation
One of the great advantages of apple-health-mcp is that no direct installation is required. You can use it directly with npx via compatible MCP clients, such as Claude Desktop.
To integrate apple-health-mcp with Claude Desktop, add the following configuration to your ~/Library/Application Support/Claude/claude_desktop_config.json file:
{
"mcpServers": {
"apple-health": {
"command": "npx",
"args": ["@neiltron/apple-health-mcp"],
"env": {
"HEALTH_DATA_DIR": "/path/to/your/health/export"
}
}
}
}
Environment Variables
Configure the server's behavior using these environment variables:
HEALTH_DATA_DIR(required): Specifies the path to your Apple Health CSV export directory.MAX_MEMORY_MB(optional): Sets the maximum memory usage in MB (default: 1024).CACHE_SIZE(optional): Determines the number of cached query results (default: 100).
Examples
Here's an example of a complete configuration for Claude Desktop:
{
"mcpServers": {
"apple-health": {
"command": "npx",
"args": ["@neiltron/apple-health-mcp"],
"env": {
"HEALTH_DATA_DIR": "/Users/yourname/Downloads/HealthAll_2025-07-202_01-04-39_SimpleHealthExportCSV",
"MAX_MEMORY_MB": "2048"
}
}
}
}
Exporting Data
To get your Apple Health data ready for apple-health-mcp:
- Download the Simple Health Export CSV app for iOS.
- In the app, tap the
Allbutton to download all data for your desired time range. - Transfer the exported ZIP file to your computer (e.g., via AirDrop).
- Unzip the file to your chosen location.
- Set the
HEALTH_DATA_DIRenvironment variable in your MCP configuration to this location.
Available Tools
Once configured, you can utilize these tools through your MCP client:
health_schema: Get information about available tables and their structure.health_query: Execute SQL queries directly on your health data.health_report: Generate comprehensive health reports.
Why Use It
apple-health-mcp offers several compelling reasons to integrate it into your health data analysis workflow:
- Natural Language Querying: Ask questions about your health data in plain English, and let the MCP client translate them into database queries.
- SQL Query Execution: For advanced users, directly execute SQL queries against your Apple Health data for precise analysis.
- Automated Reports: Generate weekly or monthly health summaries effortlessly, helping you track trends over time.
- Efficient Data Loading: Benefit from lazy loading with configurable time windows, optimizing performance for large datasets.
- Smart Caching: Query results are cached with a configurable TTL (Time To Live), ensuring faster access to frequently requested data.
This project transforms raw Apple Health data into actionable insights, making personal health analysis more accessible and powerful.
Links
- GitHub Repository: neiltron/apple-health-mcp
- Simple Health Export CSV App: Simple Health Export CSV
Related repositories
Similar repositories that may be relevant next.

code-session-memory: Automatic Vector Memory for AI Coding Sessions
August 15, 2026
code-session-memory provides automatic vector memory for various AI coding tools like OpenCode, Claude Code, Cursor, VS Code, Codex, and Gemini CLI. It indexes new messages into a vector database after each AI agent turn, enabling semantic search across all your past coding sessions. This tool ensures memory is shared across different platforms, enhancing developer productivity.

Cloudflare Computer: Give Your Agent a Virtual Filesystem
August 14, 2026
Cloudflare Computer is an innovative project that provides a virtual filesystem within a Durable Object, allowing agents to interact with a persistent state. It offers pluggable execution backends, including containerized Linux environments and serverless Workers, enabling flexible and powerful agent computing. Currently in preview, it's ideal for experiments and prototypes leveraging Cloudflare's edge infrastructure.

SwarmClaw: Self-Hosted AI Agent Runtime for Autonomous Swarms
August 13, 2026
SwarmClaw is an open-source, self-hosted AI agent runtime and multi-agent framework designed for autonomous agent swarms. It offers durable agent memory, MCP tools, schedules, and delegation, supporting over 23 LLM providers including Claude, GPT, Gemini, OpenRouter, and Ollama. This platform serves as a practical alternative to solutions like Claude Code and LangChain for those seeking self-hosted AI agent orchestration.

json-render: The Generative UI Framework for Dynamic Interfaces
August 12, 2026
json-render is a powerful Generative UI framework that allows developers to create dynamic, personalized user interfaces from natural language prompts. It ensures reliability by constraining AI-generated output to predefined components and actions, offering a predictable and safe way to build cross-platform UIs.
Source repository
Open the original repository on GitHub.
9 counted GitHub visits