How to Use the Withings MCP in Pydantic AI

Q: How can I validate weight data with Withings and pydantic-ai?

Call getmeasurements using meastype 1. Since the response is validated against Pydantic models, you're guaranteed that the resulting weight field will be correctly typed and structured.

Q: Does pydantic-ai handle workout data from Withings?

Yes, getworkouts pulls detailed exercise records. The structure of distance, duration, calories burned, and activity category are all type-checked upon receipt, preventing bad data from entering your agent's logic.

Q: What is the process for checking heart rate with Withings and pydantic-ai?

You use getheartrate to pull the measurements. Pydantic validation ensures that the returned heartbeat value is correctly typed, giving you high confidence in the data your agent processes.

Validate with confidence: Use the Withings MCP Server via Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Withings to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get detailed physiological measurements using MCP Server

The `get_measurements` tool lets you filter data by specific types—weight (1), height (4), or BP. Because of Pydantic's validation, if the API sends an unexpected field name, your agent fails loudly instead of silently corrupting data.

Monitor activity and sleep cycles with pydantic-ai

You can pull daily activity summaries using `get_activity`. For rest, both `get_sleep_summary` and `get_sleep_details` are available. Pydantic ensures that the returned data structure for these cycles is exactly what your agent expects.

Subscribe to health events with MCP Server

Use `subscribe_notifications` to get immediate alerts. You select an app code, like 16 for activity or 44 for sleep. This method guarantees that the notification payload adheres strictly to your defined Pydantic schemas.

Setup guide

Set up Withings MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "withings-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Withings tools.",
)

result = await agent.run("List recent Withings transactions")
print(result.output)

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 Pydantic AI

Call `get_measurements` using meastype 1. Since the response is validated against Pydantic models, you're guaranteed that the resulting weight field will be correctly typed and structured.

Yes, `get_workouts` pulls detailed exercise records. The structure of distance, duration, calories burned, and activity category are all type-checked upon receipt, preventing bad data from entering your agent's logic.

You use `get_heart_rate` to pull the measurements. Pydantic validation ensures that the returned heartbeat value is correctly typed, giving you high confidence in the data your agent processes.

Beyond weight and blood pressure, the server handles body temperature (71) and can also list user goals via `get_user_goals`. All these fields are type-checked for reliability.

The server touches multiple types of physiological measurements, including weight, blood pressure (systolic/diastolic), body temperature, and heart rate pulses. All are validated.

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