How to Use the Withings MCP in CrewAI

Q: How does CrewAI handle Withings workout data?

You can assign an agent to use getworkouts. One agent fetches the raw running or cycling data, and a second agent specializes in calculating metrics like total calorie burn. The collaboration ensures all fields are properly analyzed.

Q: What happens if I need sleep analysis with CrewAI?

The 'analyst' agent can be tasked with using both getsleepsummary and getsleepdetails. It compares the recorded stages against expected patterns, producing a comprehensive report without manual steps.

Q: Does Withings support notifications with CrewAI?

The 'monitor' agent uses subscribenotifications to listen for triggers, like when the user records body temperature. When an event fires, the entire crew can react by fetching related data.

Run autonomous health analysis with CrewAI's specialized agents for Withings data.

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 CrewAI

Create your Vinkius account to connect Withings to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Activity Analysis

One agent researches daily activity using `get_activity` (steps/calories), while a second analyzes the findings against `get_user_goals`. CrewAI runs these agents collaboratively, passing shared memory of the data to ensure nothing is missed. This process simulates real-world health coaching. You set up the 'research' role with `get_daily_activity` and let the 'analyst' agent evaluate it against the user’s targets.

Deep Physiological Data Reporting

`get_measurements` lets you fetch detailed stats—like systolic/diastolic BP or body temperature. A specialized 'reporter' agent can systematically gather these metrics, ensuring all required types (e.g., Type 10 for Systolic BP) are queried and compiled. Because of CrewAI’s shared memory, the agents don't just run in isolation; they pass the initial `get_measurements` data to subsequent tools, making the final report coherent.

Monitor and React to Health Events

An 'event monitor' agent watches for critical updates using `subscribe_notifications`. This is useful when tracking weight changes (Appli code 1). The subsequent 'action' agent can then automatically check the user’s current goals (`get_user_goals`) and generate an alert. This autonomous setup means you don't need human intervention; the monitoring and response happen in sequence.

Setup guide

Set up Withings MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Withings tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Withings Analyst",
    goal="Access and analyze Withings data via MCP.",
    backstory="Expert analyst with direct Withings access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Withings transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Withings Analyst",
        goal="Access and analyze Withings data via MCP.",
        backstory="Expert analyst with direct Withings access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Withings transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can assign an agent to use `get_workouts`. One agent fetches the raw running or cycling data, and a second agent specializes in calculating metrics like total calorie burn. The collaboration ensures all fields are properly analyzed.

The 'analyst' agent can be tasked with using both `get_sleep_summary` and `get_sleep_details`. It compares the recorded stages against expected patterns, producing a comprehensive report without manual steps.

Yes. You can build an autonomous operation where one agent retrieves user goals via `get_user_goals` and another compares those targets against current readings from `get_activity`. The result is a clear pass/fail status.

The 'monitor' agent uses `subscribe_notifications` to listen for triggers, like when the user records body temperature. When an event fires, the entire crew can react by fetching related data.

The server provides access to physiological measurements including weight, height, blood pressure (diastolic/systolic), body temperature, heart rate, and sleep cycle stages. These are the key data points your agents can process.

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