oura-mcp-server-enhanced

oura-mcp-server-enhanced

Comprehensive MCP server for the Oura Ring API v2, exposing 17 tools to access sleep, activity, heart rate, stress, SpO2, workouts, and user data.

Category
访问服务器

README

Oura MCP Server (Enhanced)

An MCP (Model Context Protocol) server that provides comprehensive access to the Oura Ring API v2. Exposes 17 tools covering sleep, activity, heart rate, stress, SpO2, workouts, and more.

Built with FastMCP and httpx.

Tools

Sleep & Recovery

Tool Description
get_sleep_data Detailed sleep sessions -- stages, heart rate, HRV, breathing rate
get_daily_sleep Daily sleep scores and contributor breakdown
get_sleep_time Recommended and actual sleep timing windows
get_daily_readiness Readiness scores and contributors (HRV balance, body temp, etc.)
get_daily_resilience Recovery capacity and stress tolerance indicators

Activity & Fitness

Tool Description
get_daily_activity Steps, calories, active time breakdown, MET levels
get_workouts Workout sessions with type, calories, distance, duration
get_sessions Guided sessions (meditation, breathing) with biometrics
get_vo2_max VO2 max cardiovascular fitness estimates

Health Vitals

Tool Description
get_heart_rate Heart rate at 5-minute intervals (uses datetime params)
get_daily_spo2 Daily blood oxygen saturation
get_daily_stress Daily stress levels and recovery summary
get_daily_cardiovascular_age Estimated cardiovascular age

User & Device

Tool Description
get_personal_info User profile (age, weight, height)
get_ring_configuration Ring model, color, firmware, setup date
get_rest_mode Rest mode periods and schedules
get_tags User-created lifestyle tags and annotations

All tools with date parameters accept optional start_date and end_date in YYYY-MM-DD format. When omitted, the Oura API defaults to recent data.

Setup

Option A: Claude Desktop Extension (recommended)

  1. Download the latest oura-mcp-server-enhanced.mcpb from Releases
  2. In Claude Desktop, go to Settings > Extensions > Advanced Settings and enable Install from file
  3. Back on the Extensions page, click Add from file and select the downloaded .mcpb file
  4. Enter your Oura API Token when prompted

Option B: Manual Setup

1. Get an Oura API Token

Go to Oura Personal Access Tokens and create a new token.

2. Install

Requires Python 3.12+ and uv.

git clone https://github.com/josuhr/oura-mcp-server-enhanced.git
cd oura-mcp-server-enhanced
uv venv && uv pip install -e .

3. Configure Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "oura": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/oura-mcp-server-enhanced", "oura-mcp-server"],
      "env": {
        "OURA_API_TOKEN": "your_token_here"
      }
    }
  }
}

Replace /path/to/oura-mcp-server-enhanced with the actual path and your_token_here with your Oura API token.

4. Run Standalone (optional)

export OURA_API_TOKEN="your_token_here"
oura-mcp-server

Building the Extension

To build the .mcpb extension bundle from source:

zip -r oura-mcp-server-enhanced.mcpb manifest.json pyproject.toml uv.lock src/ .python-version -x "src/**/__pycache__/*"

Project Structure

src/oura_mcp_server/
├── __init__.py       # Package entry point
├── server.py         # FastMCP tool definitions and main()
├── client.py         # Async HTTP client for Oura API v2
└── transforms.py     # Human-readable data formatting

Credits

Inspired by tomekkorbak/oura-mcp-server, extended to cover the full Oura API v2.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选