Withings MCP Client

Withings MCP Client

Enables retrieval of health data from Withings smart scales including weight measurements and comprehensive body composition metrics like fat mass, muscle mass, and hydration levels. Supports multiple users, unit preferences, and OAuth authentication for secure access to personal health data.

Category
访问服务器

README

Withings MCP Client

MCP (Model Context Protocol) client for retrieving data from Withings smart scale, including weight and body composition measurements.

Prerequisites

  1. Create a Withings Developer account at https://developer.withings.com/
  2. Create an application to get your Client ID and Client Secret
  3. Set up your redirect URI (default: http://localhost:3000/callback)
  4. Bun runtime (recommended) or Node.js

Installation

Install from GitHub

With Bun (recommended):

bun install git+https://github.com/gchallen/withings-mcp.git

Or with npm:

npm install git+https://github.com/gchallen/withings-mcp.git

Or run directly from GitHub

With Bun (recommended):

bunx --bun gchallen/withings-mcp

Or with npm/npx:

npx gchallen/withings-mcp

Setup

1. Configuration

Create a .env file with your Withings credentials:

WITHINGS_CLIENT_ID=your_client_id
WITHINGS_CLIENT_SECRET=your_client_secret
WITHINGS_REDIRECT_URI=http://localhost:3000/callback
WITHINGS_USER_ATTRIB=0  # Optional: Pin to specific user (0=device owner, 1+=other users)
WITHINGS_UNIT_SYSTEM=imperial  # Optional: Set default units (metric=kg, imperial=lb)

2. Authorization (One-time setup)

Before using the MCP server, you need to authorize access to your Withings data. Run the authorization tool:

With Bun:

bun tokens

Or directly from GitHub:

bunx --bun gchallen/withings-mcp tokens
# or
npx gchallen/withings-mcp tokens

Or after cloning:

git clone https://github.com/gchallen/withings-mcp.git
cd withings-mcp
bun tokens
# or
npm run tokens

This will:

  1. Start a temporary local server on port 3000
  2. Open your browser to the Withings authorization page
  3. Handle the OAuth callback automatically
  4. Save your access and refresh tokens to the .env file
  5. Shut down the temporary server

The authorization is only needed once. The MCP server will automatically refresh tokens as needed.

CLI Usage

The package provides a unified CLI with the following commands:

# Run OAuth authorization (one-time setup)
bunx --bun gchallen/withings-mcp tokens
# or
npx gchallen/withings-mcp tokens

# Start the MCP server (default command)
bunx --bun gchallen/withings-mcp
# or
npx gchallen/withings-mcp

Available Tools

The MCP server provides the following tools:

withings_get_weight

Get the latest weight measurement from your Withings scale.

withings_get_body_composition

Get complete body composition data including:

  • Weight (kg)
  • Fat mass (kg and percentage)
  • Muscle mass (kg and percentage)
  • Bone mass (kg and percentage)
  • Hydration (kg and percentage)
  • Visceral fat index
  • Metabolic age

withings_get_measurements

Get raw measurement data with optional filters.

Parameters:

  • measureTypes (optional): Array of measurement type IDs
  • startDate (optional): Start date in ISO format
  • endDate (optional): End date in ISO format
  • userAttrib (optional): User attribution filter

withings_get_users

Get list of users who have measurements on the Withings scale.

Returns user statistics including measurement counts and latest measurement dates.

User Filtering

All tools support filtering by user attribution:

  • userAttrib: 0 - Device owner (primary user)
  • userAttrib: 1+ - Other users
  • userAttrib: 2 - Manual entries
  • userAttrib: 4 - Automatic detection

You can set WITHINGS_USER_ATTRIB environment variable to automatically filter all requests to a specific user. If not set, data from all users will be returned (unless explicitly filtered).

Unit System

All measurement tools support both metric and imperial units:

  • unitSystem: "metric" - Returns weights in kg
  • unitSystem: "imperial" - Returns weights in lb

You can set WITHINGS_UNIT_SYSTEM environment variable to automatically use your preferred units for all requests:

  • WITHINGS_UNIT_SYSTEM=metric - Default, returns kg/cm
  • WITHINGS_UNIT_SYSTEM=imperial - Returns lb/inches

If not set, defaults to metric. You can override on a per-request basis by passing the unitSystem parameter to individual tools.

Usage with Claude Desktop

Add the server to your Claude Desktop configuration:

With Bun (recommended):

{
  "mcpServers": {
    "withings": {
      "command": "bunx",
      "args": ["--bun", "gchallen/withings-mcp"],
      "env": {
        "WITHINGS_CLIENT_ID": "your_client_id",
        "WITHINGS_CLIENT_SECRET": "your_client_secret",
        "WITHINGS_REDIRECT_URI": "http://localhost:3000/callback",
        "WITHINGS_ACCESS_TOKEN": "your_access_token",
        "WITHINGS_REFRESH_TOKEN": "your_refresh_token",
        "WITHINGS_USER_ATTRIB": "0",
        "WITHINGS_UNIT_SYSTEM": "imperial"
      }
    }
  }
}

Or with npm:

{
  "mcpServers": {
    "withings": {
      "command": "npx",
      "args": ["gchallen/withings-mcp"],
      "env": {
        "WITHINGS_CLIENT_ID": "your_client_id",
        "WITHINGS_CLIENT_SECRET": "your_client_secret",
        "WITHINGS_REDIRECT_URI": "http://localhost:3000/callback",
        "WITHINGS_ACCESS_TOKEN": "your_access_token",
        "WITHINGS_REFRESH_TOKEN": "your_refresh_token",
        "WITHINGS_USER_ATTRIB": "0",
        "WITHINGS_UNIT_SYSTEM": "imperial"
      }
    }
  }
}

Note: After running the auth command, the access and refresh tokens will be saved to your .env file. Copy these values to your Claude Desktop configuration.

Development

Clone the Repository

For local development:

git clone https://github.com/gchallen/withings-mcp.git
cd withings-mcp
bun install  # or npm install

Build

bun run build  # or npm run build

Run in development mode

bun dev        # or npm run dev

Run tests

bun test       # or npm test

Lint and format

bun lint       # or npm run lint
bun format     # or npm run format

License

ISC

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