How to Use the Withings MCP in Vercel AI SDK

Q: Can I use Withings weight data with Vercel AI SDK?

Yep. You can call getmeasurements and specify 'Weight' (Type 1) to get the latest readings. Since it streams, your UI updates fast when checking a user's current weight.

Q: Does Withings support notifications with Vercel AI SDK?

Yes, you can use subscribenotifications. This tool lets your agent listen for events—for instance, notifying the user immediately after they step on a scale. The result is fast and visible in your application.

Stream live health data into your UI with the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Withings to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Display Activity Data in Real Time

The `get_activity` tool pulls daily summaries, giving you steps and calories right when the user needs it. Because this runs on the Vercel AI SDK, the data streams directly into your React or Next.js frontend; users see the numbers update live instead of waiting for a loading spinner. This real-time flow makes building interactive health dashboards simple. You can call `get_activity` and let the user watch the daily totals appear in their browser as they are being fetched.

Check Sleep Patterns Instantly

`get_sleep_summary` grabs the day's sleep data, including key states. With your AI client running on Vercel AI SDK, you can display these summaries instantly, providing immediate feedback to the user. Need more detail? Use `get_sleep_details` for granular info like specific stages. This rapid streaming capability means the whole experience feels snappy and responsive across all devices.

Build Custom Workout Logs

`get_workouts` pulls records for runs, swims, or cycles, detailing distance, calories, and duration. When integrating this with your front-end using the Vercel AI SDK, you get a smooth experience where workout data pops up instantly. It's quick to display results from `get_user_goals`, letting users see what they were aiming for right next to their actual recorded activity.

Setup guide

Set up Withings MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Withings tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Withings transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

The Vercel AI SDK streams MCP tool results directly into your UI. When you run a query, like checking `get_heart_rate`, the user sees the data appearing live, not after a delay or loading screen.

Yep. You can call `get_measurements` and specify 'Weight' (Type 1) to get the latest readings. Since it streams, your UI updates fast when checking a user's current weight.

Yes, you can use `subscribe_notifications`. This tool lets your agent listen for events—for instance, notifying the user immediately after they step on a scale. The result is fast and visible in your application.

You can access several types of measurements, including weight (Type 1), blood pressure (Types 9 and 10), body temperature (Type 71), and heart rate. These are all exposed via the `get_measurements` tool.

This MCP Server accesses physiological measurements, specifically weight, height, blood pressure, heart rate, body temperature, and sleep cycle data. Your agent handles this data flow via the streaming API.

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