Apple Health MCP Server

📋 Table of Contents

• 🔍 About
• 💡 Demo
• 🚀 Getting Started
• 📝 Usage
• 🔧 Configuration
• 🐳 Docker Setup
• 🛠️ MCP Tools
• 🗺️ Roadmap
• 👥 Contributors
• 📄 License

🔍 About The Project

Apple Health MCP Server implements a Model Context Protocol (MCP) server designed for seamless interaction between LLM-based agents and Apple Health data. It provides a standardized interface for querying, analyzing, and managing Apple Health records—imported from XML exports and indexed in Elasticsearch—through a comprehensive suite of tools. These tools are accessible from MCP-compatible clients (such as Claude Desktop), enabling users to explore, search, and analyze personal health data using natural-language prompts and advanced filtering, all without requiring direct knowledge of the underlying data formats or Elasticsearch queries.

✨ Key Features

• 🚀 FastMCP Framework: Built on FastMCP for high-performance MCP server capabilities
• 🍏 Apple Health Data Management: Import, parse, and analyze Apple Health XML exports
• 🔎 Powerful Search & Filtering: Query and filter health records using natural language and advanced parameters
• 📦 Elasticsearch Integration: Index and search health data efficiently at scale
• 🛠️ Modular MCP Tools: Tools for structure analysis, record search, type-based extraction, and more
• 📈 Data Summaries & Trends: Generate statistics and trend analyses from your health data
• 🐳 Container Ready: Docker support for easy deployment and scaling
• 🔧 Configurable: Extensive .env-based configuration options

🏗️ Architecture

The Apple Health MCP Server is built with a modular, extensible architecture designed for robust health data management and LLM integration:

• MCP Tools: Dedicated tools for Apple Health XML structure analysis, record search, type-based extraction, and statistics/trend generation. Each tool is accessible via the MCP protocol for natural language and programmatic access.
• XML Import & Parsing: Efficient streaming and parsing of large Apple Health XML exports, extracting records, workouts, and metadata for further analysis.
• Elasticsearch Backend: All health records are indexed in Elasticsearch, enabling fast, scalable search, filtering, and aggregation across large datasets.
• Service Layer: Business logic for XML and Elasticsearch operations is encapsulated in dedicated service modules, ensuring separation of concerns and easy extensibility.
• FastMCP Framework: Provides the MCP server interface, routing, and tool registration, making the system compatible with LLM-based agents and MCP clients (e.g., Claude Desktop).
• Configuration & Deployment: Environment-based configuration and Docker support for easy setup and deployment in various environments.

(back to top)

💡 Demo

This demo shows how Claude uses the apple-health-mcp-server to answer questions about your data. Example prompts from the demo:

• I would like you to help me analyze my Apple Health data. Let's start by analyzing the data types - check what data is available and how much of it there is.
• What can you tell me about my activity in the last week? How did my daily statistics look?
• Please also summarise my running workouts in July and June. Do you see anything interesting?

https://github.com/user-attachments/assets/93ddbfb9-6da9-42c1-9872-815abce7e918

🚀 Getting Started

Follow these steps to set up Apple Health MCP Server in your environment.

Prerequisites

• Docker (recommended) or uv + docker: For dependency management

  👉 uv Installation Guide

• Clone the repository:

  git clone https://github.com/the-momentum/apple-health-mcp-server
  cd apple-health-mcp-server
  

• Set up environment variables:

  cp config/.env.example config/.env
  

  Edit the config/.env file with your credentials and configuration. See Environment Variables

Prepare Your Data

1. Export your Apple Health data as an XML file from your iPhone and place it somewhere in your filesystem. By default, the server expects the file in the project root directory.

• if you need working example, we suggest this dataset: https://drive.google.com/file/d/1bWiWmlqFkM3MxJZUD2yAsNHlYrHvCmcZ/view?usp=drive_link
  • Rob Mulla. Predict My Sleep Patterns. https://kaggle.com/competitions/kaggle-pog-series-s01e04, 2023. Kaggle.

2. Prepare an Elasticsearch instance and populate it from the XML file:
   • Run make es to start Elasticsearch and import your XML data.
   • (Optional) To clear all data from the Elasticsearch index, run:

     uv run python scripts/xml2es.py --delete-all
     

Configuration Files

You can run the MCP Server in your LLM Client in two ways:

• Docker (recommended)
• Local (uv run)

Docker MCP Server

1. Build the Docker image:

   make build
   

2. Add the following config to your LLM Client settings (replace <project-path> with your local repository path and <xml-file-name> with name of your raw data from apple healt file (without .xml extension)):

   {
     "mcpServers": {
       "docker-mcp-server": {
         "command": "docker",
         "args": [
           "run",
           "-i",
           "--rm",
           "--init",
           "--mount",
           "type=bind,source=<project-path>/{xml-file-name}.xml,target=/root_project/raw.xml",
           "--mount", // optional - volume for reload
           "type=bind,source=<project-path>/app,target=/root_project/app", // optional
           "--mount",
           "type=bind,source=<project-path>/config/.env,target=/root_project/config/.env",
           "-e",
           "ES_HOST=host.docker.internal",
           "mcp-server:latest"
         ]
       }
     }
   }
   

Local uv MCP Server

1. Get the path to your uv binary:
   • On Windows:

     (Get-Command uv).Path
     

   • On MacOS/Linux:

     which uv
     

2. Add the following config to your LLM Client settings (replace <project-path> and <path-to-bin-folder> as appropriate):

   {
     "mcpServers": {
       "uv-mcp-server": {
         "command": "uv",
         "args": [
           "run",
           "--frozen",
           "--directory",
           "<project-path>",
           "start"
         ],
         "env": {
           "PATH": "<path-to-uv-bin-folder>"
         }
       }
     }
   }
   

   • <path-to-uv-bin-folder> should be the folder containing the uv binary (do not include uv itself at the end).

3. Restart Your MCP Client

After completing the above steps, restart your MCP Client to apply the changes. In some cases, you may need to terminate all related processes using Task Manager or your system's process manager to ensure:

• The updated configuration is properly loaded
• Environment variables are correctly applied
• The Apple Health MCP client initializes with the correct settings

(back to top)

🔧 Configuration

Environment Variables

Note: All variables below are optional unless marked as required. If not set, the server will use the default values shown. Only RAW_XML_PATH is required and must point to your Apple Health XML file.

(back to top)

🛠️ MCP Tools

The Apple Health MCP Server provides a suite of tools for exploring, searching, and analyzing your Apple Health data, both at the raw XML level and in Elasticsearch:

XML Tools (xml_reader)

Elasticsearch Tools (es_reader)

All tools are accessible via MCP-compatible clients and can be used with natural language or programmatic queries to explore and analyze your Apple Health data.

(back to top)

🗺️ Roadmap

We're continuously enhancing Apple Health MCP Server with new capabilities. Here's what's on the horizon:

• Time Series Sampling During Import: Add advanced analytical tools to sample and generate time series data directly during the XML-to-Elasticsearch loading process.
• Optimized XML Tools: Improve the performance and efficiency of XML parsing and querying tools.
• Expanded Elasticsearch Analytics: Add more advanced analytics and aggregation functions to the Elasticsearch toolset.
• Embedded Database Tools: Integrate tools for working with embedded databases for local/offline analytics and storage.

Have a suggestion? We'd love to hear from you! Contact us or contribute directly.

👥 Contributors

(back to top)

📄 License

Distributed under the MIT License. See MIT License for more information.