Ultrahuman MCP Server
Enables fetching health and fitness metrics from the Ultrahuman API, including heart rate, sleep, steps, temperature, and HRV data.
README
Ultrahuman MCP Server
A Model Context Protocol (MCP) server for fetching health and fitness metrics from the Ultrahuman API. Built with TypeScript and designed for production use.
🚀 Quick Start
- Clone the repository
- Install dependencies:
bun install - Build the project:
bun run build - Configure your environment variables (see Configuration section)
- Add to Claude Desktop (see Usage section)
🔑 Getting Started with Ultrahuman API
Before you can use this MCP server, you'll need to obtain your Ultrahuman credentials. Follow these steps:
Step 1: Get Your Ultrahuman Email
- Open the Ultrahuman app on your device
- Navigate to the Profile tab at the bottom of the screen
- Tap the settings icon (cog icon) in the top left corner
- Your email address will be displayed at the top of the settings screen
- Copy this email address - you'll need it for configuration
Step 2: Request API Key and Partner ID
You must obtain an API key and Partner ID from Ultrahuman by contacting them through one of these methods:
- Email: Send a request to
support@ultrahuman.com - In-app chat: Use the customer service chat within the Ultrahuman app
Important: Make sure to include your Ultrahuman email address in your request to speed up the response time.
Once you receive your API key and Partner ID, keep them secure and private.
Step 3: Configure Partner ID in App
- Open the Ultrahuman app on your device
- Navigate to the Profile tab at the bottom of the screen
- Tap the settings icon (cog icon) in the top left corner
- Scroll down to find the Partner ID field
- Enter the Partner ID code you received from Ultrahuman
Step 4: Configure the MCP Server
Now you can configure this MCP server with your credentials:
- Set your environment variables (see Configuration section below)
- Build and run the server
- Add it to Claude Desktop with your API credentials
You're all set to start fetching your health data!
✨ Key Features
- Fetch comprehensive health metrics from Ultrahuman API
- Heart rate, sleep, steps, temperature, and HRV monitoring
- Built with TypeScript for type safety
- Bun for fast testing and development
- Biome for linting and formatting
- Clean, maintainable project structure
📂 Project Structure
ultrahuman-mcp/
├── src/
│ ├── tools/ # MCP tools implementation
│ │ └── ultrahumanMetrics/ # Ultrahuman API integration
│ ├── utils/ # Shared utilities
│ ├── main.ts # Server entry point
│ └── types.ts # Shared type definitions
├── scripts/ # Build and utility scripts
├── biome.json # Linting configuration
├── tsconfig.json # TypeScript configuration
└── package.json # Project dependencies
⚙️ Configuration
This server requires environment variables to authenticate with the Ultrahuman API:
ULTRAHUMAN_AUTH_TOKEN: Your Ultrahuman API authorization tokenULTRAHUMAN_USER_EMAIL: The email address of the Ultrahuman user whose data you want to fetch
The API base URL is configured to https://partner.ultrahuman.com/api/v1.
🔧 Available Tools
ultrahuman_metrics
Fetches health and fitness metrics from the Ultrahuman API for a specific date. The user email is configured via environment variable, so you only need to specify the date to retrieve comprehensive health data.
Parameters:
date: Date in YYYY-MM-DD format to fetch metrics for (e.g., '2025-06-19')
Example Usage:
{
"name": "ultrahuman_metrics",
"arguments": {
"date": "2025-06-19"
}
}
📊 Available Health Data
The API provides comprehensive health metrics including:
- Heart Rate: Continuous heart rate monitoring with timestamps
- Skin Temperature: Body temperature variations throughout the day
- HRV (Heart Rate Variability): Heart rate variability measurements
- Steps: Step count data with activity tracking
- Sleep Data: Detailed sleep analysis including:
- Sleep stages (Deep, Light, REM, Awake)
- Sleep efficiency and quality metrics
- Heart rate and HRV during sleep
- Temperature variations during sleep
- Recovery Index: Overall recovery score
- Movement Index: Activity and movement metrics
- VO2 Max: Cardiovascular fitness indicator
💻 Usage with Claude Desktop
-
Build the project:
bun run build -
Add to your Claude Desktop config (
~/Library/Application Support/Claude/claude_desktop_config.json):{ "mcpServers": { "ultrahuman": { "command": "node", "args": ["/path/to/your/project/dist/main.js"], "env": { "ULTRAHUMAN_AUTH_TOKEN": "your_token_here", "ULTRAHUMAN_USER_EMAIL": "your_email@example.com" } } } }
🧪 Testing
You can test the server by running it directly:
node dist/main.js
The server will listen for MCP requests on stdio and provide the ultrahuman_metrics tool to fetch health data from the API.
🛠️ Development
- Run tests:
bun test - Format code:
bun run format - Lint code:
bun run lint - Build project:
bun run build
📜 Version Management
This project uses standard-version for automated version management. Run bun run release to create a new version.
Commit Message Format
feat: New feature (bumps minor version)fix: Bug fix (bumps patch version)BREAKING CHANGE: Breaking change (bumps major version)
📦 Publishing to npm
- Ensure you're logged in to npm:
npm login - Build the project:
bun run build - Publish the package:
npm publish
Installing from npm (after publishing)
Add to your Claude Desktop config:
{
"mcpServers": {
"ultrahuman": {
"command": "npx",
"args": ["-y", "ultrahuman-mcp"],
"env": {
"ULTRAHUMAN_AUTH_TOKEN": "your_token_here",
"ULTRAHUMAN_USER_EMAIL": "your_email@example.com"
}
}
}
}
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。