How to Use the WHOOP MCP in AutoGen

Q: Can AutoGen use WHOOP data to check body metrics?

Yes. An agent can call getbodymeasurement and then present those findings alongside more cyclical data, such as pulling recent workout totals from getworkouts.

Q: How do I ensure AutoGen uses the latest WHOOP profile info?

The agent starts by calling getprofile. This initial step ensures all subsequent calls for historical data are tied to the correct user identity via the MCP Server.

Build deliberative WHOOP agents using AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WHOOP MCP to AutoGen

Create your Vinkius account to connect WHOOP to AutoGen 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 WHOOP with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Optimal WHOOP Strategy with AutoGen

You set up multiple agents to argue over a user's fitness plan. One agent calls `get_cycles` for historical data, while another uses `get_body_measurement`. They debate whether the low recovery score was due to poor sleep or high strain. The outcome isn't just an API dump; it’s a negotiated conclusion. The agents challenge assumptions until they converge on the most probable cause based on the gathered WHOOP metrics.

MCP Server for Multi-Metric WHOOP Analysis

An AutoGen system can manage complex, multi-step analysis by calling `get_sleep` and then feeding those results to a specialized agent. That second agent might then call `get_cycle_sleep` to confirm the sleep stages and disturbances. The workflow requires deliberation: one agent reads the raw data from `get_workouts`, another checks for body measurements via `get_body_measurement`, leading to an actionable insight.

Managing WHOOP Data Streams with AutoGen

The framework excels at managing date ranges. If you need to know if the recent poor recovery was a pattern, agents can sequentially call `get_recovery` and `get_sleep`, comparing trends across multiple requested dates. The system's power is in its negotiation: one agent pulls sleep data (`get_sleep`), another checks for strain (`get_workouts`), and they argue about which metric needs the most attention.

Setup guide

Set up WHOOP MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes WHOOP tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="WHOOP_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent WHOOP data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="WHOOP_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent WHOOP data")
    print(result.messages[-1].content)

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 WHOOP. 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 WHOOP 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 WHOOP MCP in AutoGen

The agents debate the findings. For example, one agent reports high strain from `get_workouts`, while another points out low recovery scores from `get_cycle_recovery`. The final output is a reasoned summary of the conflict.

Yes. An agent can call `get_body_measurement` and then present those findings alongside more cyclical data, such as pulling recent workout totals from `get_workouts`.

The MCP Server exposes a wide range of metrics. You'll find sleep stages (from `get_sleep`), heart rate variability, strain balance, and GPS workout data.

The agent starts by calling `get_profile`. This initial step ensures all subsequent calls for historical data are tied to the correct user identity via the MCP Server.

It helps manage contextually. When querying, it knows which specific data types—like `body_measurement` readings—are being accessed and discussed among the agents.

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