Withings

Provides a Withings MCP Server to access weight, body composition, and measurement data from Withings scales.

typescript

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "gchallen-withings-mcp": {
      "command": "bunx",
      "args": [
        "--bun",
        "gchallen/withings-mcp"
      ],
      "env": {
        "WITHINGS_CLIENT_ID": "YOUR_CLIENT_ID",
        "WITHINGS_UNIT_SYSTEM": "metric",
        "WITHINGS_USER_ATTRIB": "0",
        "WITHINGS_REDIRECT_URI": "http://localhost:3000/callback",
        "WITHINGS_CLIENT_SECRET": "YOUR_CLIENT_SECRET"
      }
    }
  }
}

You can use this MCP server to fetch data from a Withings smart scale, including weight and detailed body composition metrics. It streamlines authentication, data retrieval, and unit handling so you can build dashboards, automations, or analytics on top of your Withings measurements.

How to use

To start using the Withings MCP Server, run it on your machine and connect through a compatible MCP client. You can perform one-time authorization to grant the server access to your Withings data, after which token refresh happens automatically. Use the available tools to fetch the latest weight, complete body composition, raw measurements, or lists of users with measurements.

How to install

Prerequisites include a modern runtime and access to Withings developer credentials. You will need a Withings Developer account, a registered application to obtain a Client ID and Client Secret, and a redirect URI (default is http://localhost:3000/callback). The runtime recommended here is Bun, but Node.js is also supported.

Install options. You can install directly from the package source and then run locally, or execute the package without installing globally.

# Install from GitHub using Bun (recommended)
bun install git+https://github.com/gchallen/withings-mcp.git

# Install from GitHub using npm
npm install git+https://github.com/gchallen/withings-mcp.git
```}]} ,{

Configuration and operational notes

Prepare a .env file with your Withings credentials and preferences. Include your Client ID, Client Secret, redirect URI, and optional user and unit preferences. The authorization process creates access and refresh tokens and stores them for automatic refreshing.

One-time authorization. Run the authorization tool to obtain tokens and set up the local server to complete the OAuth flow.

Two common ways to start the MCP server locally are shown here. Use the one that matches your preferred runtime.

Troubleshooting and tips

If you encounter authentication issues, ensure your redirect URI matches exactly what you configured in Withings and that your Client ID/Secret are correct. Token refresh happens automatically after initial authorization.

Notes on usage with clients

The server provides tools to query data. You can filter by user attribution, switch between metric and imperial units, and query by date ranges when retrieving measurements.

Available tools

withings_get_weight

Fetches the latest weight measurement from your Withings scale.

withings_get_body_composition

Retrieves complete body composition data including weight, fat/muscle/bone mass, hydration, visceral fat index, and metabolic age.

withings_get_measurements

Fetches raw measurement data with optional filters such as measureTypes, startDate, endDate, and userAttrib.

withings_get_users

Returns a list of users who have measurements on the scale, including their latest measurement dates.

Built by

VeilStrat

AI signals for GTM teams