Apple Health
A Model Context Protocol server that enables seamless interaction between LLM-based agents and Apple Health data, allowing users to query, analyze, and manage health records through natural language commands.
What is Apple Health?
Apple Health is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that enables seamless interaction between llm-based agents and apple health data, allowing users to query, analyze, and manage health records through natural language com...
A Model Context Protocol server that enables seamless interaction between LLM-based agents and Apple Health data, allowing users to query, analyze, and manage health records through natural language commands.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol server that enables seamless intera
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx apple-health-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Apple Health
The Apple Health MCP Server connects AI assistants to your personal Apple Health data by reading CSV exports produced by the 'Simple Health Export CSV' iOS app. It exposes a SQL-queryable interface over your health records, letting you run natural language queries that get translated into structured data lookups across metrics like steps, heart rate, sleep, and workouts. This is a fully local, privacy-preserving integration — no data leaves your machine and no API keys are required.
Prerequisites
- Node.js 18+ installed (for npx)
- An iPhone with Apple Health data and the 'Simple Health Export CSV' app installed (free on the App Store)
- A valid Apple Health CSV export unzipped to a local directory
- An MCP-compatible client such as Claude Desktop
Export your Apple Health data
On your iPhone, open the 'Simple Health Export CSV' app, tap 'All' to select all data types and your desired time range, then tap Export. AirDrop or transfer the resulting ZIP file to your Mac. Unzip it to a permanent directory such as ~/health-data.
unzip apple-health-export.zip -d ~/health-dataVerify Node.js is available
Ensure you have Node.js 18 or higher installed so that npx can run the server package without a separate global install.
node --versionTest the server manually
Run the server once interactively to confirm it can find and parse your export directory before wiring it into a client.
HEALTH_DATA_DIR=~/health-data npx @neiltron/apple-health-mcpAdd the server to Claude Desktop
Open ~/Library/Application Support/Claude/claude_desktop_config.json and add the apple-health entry under mcpServers. Set HEALTH_DATA_DIR to the absolute path where you unzipped the export.
Restart Claude Desktop and verify
Quit and reopen Claude Desktop. In a new conversation, ask Claude to list the available health tables — you should see a response from the health_schema tool confirming the data is accessible.
Apple Health Examples
Client configuration
Add this block to your claude_desktop_config.json under the mcpServers key. Replace the HEALTH_DATA_DIR path with the actual location of your unzipped Apple Health CSV export.
{
"mcpServers": {
"apple-health": {
"command": "npx",
"args": ["@neiltron/apple-health-mcp"],
"env": {
"HEALTH_DATA_DIR": "/Users/yourname/health-data"
}
}
}
}Prompts to try
Once configured, use these prompts in Claude Desktop to explore your health data.
- "What health data tables are available in my Apple Health export?"
- "Show me my average daily step count for the past 30 days."
- "Generate a weekly heart rate summary for last month."
- "How many hours of sleep did I average this week?"
- "Create a monthly health report covering steps, sleep, and resting heart rate."Troubleshooting Apple Health
Server starts but returns no data or empty tables
Confirm that HEALTH_DATA_DIR points to the directory containing the CSV files, not the ZIP itself. Run 'ls $HEALTH_DATA_DIR' to verify CSV files are present.
'npx @neiltron/apple-health-mcp' is not found or fails to install
Make sure you are using Node.js 18+. Run 'node --version' to check. If the package name differs, check the GitHub releases page at https://github.com/neiltron/apple-health-mcp for the current published package name.
High memory usage when querying large exports
Set the MAX_MEMORY_MB environment variable to limit memory consumption (default is 1024 MB). For very large exports spanning multiple years, consider filtering the CSV export to a shorter time range.
Frequently Asked Questions about Apple Health
What is Apple Health?
Apple Health is a Model Context Protocol (MCP) server that model context protocol server that enables seamless interaction between llm-based agents and apple health data, allowing users to query, analyze, and manage health records through natural language commands. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Apple Health?
Follow the installation instructions on the Apple Health GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Apple Health?
Apple Health works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Apple Health free to use?
Yes, Apple Health is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Apple Health Alternatives — Similar Business Applications Servers
Looking for alternatives to Apple Health? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Apple Health in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Apple Health?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.