How do I filter for specific measurements like Body Fat or Blood Pressure?

Use the `meastype` parameter with the `get_measurements` tool. Common types: 1 (Weight), 4 (Height), 8 (Fat Mass), 9 (Diastolic BP), 10 (Systolic BP), 11 (Heart Pulse), 71 (Body Temperature).

What is the difference between sleep summary and sleep details?

`get_sleep_summary` returns one overall score and total duration per night. `get_sleep_details` returns high-frequency intraday data, detailing exactly what time you entered REM, deep sleep, or woke up throughout the night.

Can I receive real-time notifications when I step on the scale?

Yes, use the `subscribe_notifications` tool with an `appli` ID of 1 (Weight). Withings will then send a POST webhook to the callback URL you specify the moment a new weight measurement is synced.

Withings MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Withings
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Withings through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Withings "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Withings?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Withings MCP Server

Connect your Withings account to any AI agent to unlock deep insights into your health, wellness, and fitness data collected by Withings smart scales, watches, and medical devices.

Pydantic AI validates every Withings tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Medical Measurements — Track weight, body fat %, systolic/diastolic blood pressure, and heart pulse trends over time
Sleep Analytics — Access daily sleep scores, deep/light/REM sleep stage durations, and sleep efficiency metrics
Activity Tracking — Analyze daily step counts, active calories burned, and precise intraday activity levels
Workout Logging — Review distinct workout sessions (running, swimming, cycling) with categorizations and duration
Device Management — Check the battery status and connection status of your Withings hardware fleet
Real-time Notifications — Configure webhooks to receive instant alerts when new measurements (like a morning weigh-in) are recorded

The Withings MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Withings to Pydantic AI via MCP

Follow these steps to integrate the Withings MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Withings with type-safe schemas

Why Use Pydantic AI with the Withings MCP Server

Pydantic AI provides unique advantages when paired with Withings through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Withings integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Withings connection logic from agent behavior for testable, maintainable code

Withings + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Withings MCP Server delivers measurable value.

Type-safe data pipelines: query Withings with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Withings tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Withings and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Withings responses and write comprehensive agent tests

Withings MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Withings to Pydantic AI via MCP:

get_activity

Get daily activity summaries (steps, calories)

get_heart_rate

Get specific heart rate measurements

get_intraday_activity

Get high-frequency intraday activity data

get_measurements

Use meastype to filter (1=Weight, 4=Height, 9=Diastolic BP, 10=Systolic BP, 11=Heart Pulse, 71=Body Temp). Dates should be YYYY-MM-DD. Get physiological measurements (weight, blood pressure, etc)

get_sleep_details

Get detailed sleep data (stages and states)

get_sleep_summary

Get daily sleep summaries

get_user_devices

List user's Withings devices

get_user_goals

Get user health and fitness goals

get_workouts

g., running, swimming, cycling) with their specific duration, calorie burn, distance, and activity category. Get recorded workouts and exercises

subscribe_notifications

g. immediately after a user steps on a scale). Appli codes: 1(weight), 4(BP), 16(activity), 44(sleep). Subscribe to Withings webhook notifications

Example Prompts for Withings in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Withings immediately.

"Retrieve my weight and body fat measurements for the last 30 days."

"What was my sleep score and total sleep time last night?"

"Analyze my activity levels over the weekend. Did I hit my step goals?"

Troubleshooting Withings MCP Server with Pydantic AI

Common issues when connecting Withings to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Withings + Pydantic AI FAQ

Common questions about integrating Withings MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Withings MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.