How to Use the Withings MCP in Mastra AI

Q: Can Mastra AI check sleep patterns from Withings?

Absolutely. The workflow engine handles calls to both getsleepsummary and getsleepdetails. You can build complex rules, like 'if deep sleep time is low, notify the user.' This ensures reliable reporting.

Q: How does Withings support notifications with Mastra AI?

You use subscribenotifications within a workflow. The system waits for specific device events, such as when a user steps on the scale (Appli code 1), and then automatically executes your defined action.

Build complex health workflows with Mastra AI's reliable MCP tool execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Withings MCP to Mastra AI

Create your Vinkius account to connect Withings to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Withings with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process Multi-Step Health Queries

The `get_measurements` tool lets you filter for specific metrics like weight, height, or blood pressure using a defined type code. With Mastra AI's workflow engine, you can chain these calls—for example, first getting 'Height' (Type 4), then fetching the current 'Weight' (Type 1)—and handle failures if one step fails. This reliability means your complex health checks don't break on bad data. Mastra AI handles retries with exponential backoff, so you get robust results even if the initial API call hiccups.

Track and Report Workouts Automatically

`get_workouts` gathers detailed exercise records (running, swimming, etc.) including distance and calories. You can build a workflow that checks for workouts today, then compares them to `get_user_goals`. If the goal wasn't met, the workflow notifies an admin. This multi-step process is perfect for complex reporting. Mastra AI ensures that if the workout data fails to load, it doesn't just fail—it tries again.

Manage User Device and Goal Status

`get_user_devices` lists all connected Withings hardware; `get_user_goals` fetches the user’s set fitness objectives. You can build a workflow that first checks which devices are online, then uses those device details to validate the goal data. Furthermore, you'll use this process when setting up monitoring via `subscribe_notifications`, allowing your system to wait for and react to scale events.

Setup guide

Set up Withings MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Withings tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "withings-mcp-client",
  servers: {
    "withings-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Withings Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Withings tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Withings transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Withings. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Withings now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Withings MCP in Mastra AI

Mastra AI allows you to build workflows that process daily activities. You can use `get_activity` and set up branching logic—for example, if steps are below a threshold, it automatically triggers an alert.

Absolutely. The workflow engine handles calls to both `get_sleep_summary` and `get_sleep_details`. You can build complex rules, like 'if deep sleep time is low, notify the user.' This ensures reliable reporting.

Mastra AI includes automatic retries with exponential backoff. If an initial call to `get_heart_rate` times out, the system automatically tries again with increasing delays until it gets a valid result.

Yes. The server touches physiological measurements like weight, blood pressure, heart rate, body temperature, and sleep cycle data. You must manage the secure flow of this health information through your workflows.

You use `subscribe_notifications` within a workflow. The system waits for specific device events, such as when a user steps on the scale (Appli code 1), and then automatically executes your defined action.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript