How to Use the WHOOP MCP in OpenAI Agents SDK

Q: How do I check for WHOOP data using the OpenAI Agents SDK?

First, use getprofile to confirm your user ID and that the connection works. After that, you can query specific cycles with getcycle or pull general recovery trends with getrecovery. The MCP Server handles the heavy lifting.

Get granular health metrics with your AI client using the WHOOP MCP Server.

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 OpenAI Agents SDK

Create your Vinkius account to connect WHOOP to OpenAI Agents 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 WHOOP with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch specific recovery data via OpenAI Agents SDK

Need to know how rested someone is? Use `get_cycle_recovery` to pull key numbers like the recovery score, resting heart rate, and HRV. It also gives you sleep balance and strain balance for that day. You can check broader trends too. The `get_recovery` tool lets you grab WHOOP recovery data across a date range, handling up to 25 results per request.

Get workout details using the MCP Server

Every agent needs to know what the user did yesterday. Call `get_workout` with an ID to get strain score, duration, and calories burned. It also pulls in heart rate zones and GPS data if it's available. For a full history, the `get_workouts` tool lets you query WHOOP workout records across dates, managing pagination up to 25 results at a time.

Retrieve detailed sleep metrics with your AI client

Don't just know 'rested.' Use `get_sleep` or `get_sleep_by_id` to see the nitty-gritty. You get total duration, sleep stages (REM, deep, light), disturbances, and a performance percentage. This data is critical for building accurate health profiles. The `get_cycles` tool lets you grab WHOOP cycle data—combining sleep, recovery, strain, and heart rate metrics—for any 24-hour period.

Setup guide

Set up WHOOP MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all WHOOP tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives WHOOP tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate WHOOP tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="WHOOP Agent",
            instructions="You have access to WHOOP tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

First, use `get_profile` to confirm your user ID and that the connection works. After that, you can query specific cycles with `get_cycle` or pull general recovery trends with `get_recovery`. The MCP Server handles the heavy lifting.

The server supports a ton. You can check body measurements via `get_body_measurement`, pull workout logs using `get_workouts`, or get sleep stages with `get_sleep_by_id`. It's comprehensive.

Yeah, it can. For instance, fetching general recovery logs uses `get_recovery` and handles pagination with up to 25 results per call. You just keep chaining those calls until you get all the data.

The server is built around fetching individual user metrics, so you'll typically need to iterate through profiles. Start by getting your own profile info using `get_profile`.

The server touches health metrics like sleep duration, recovery score, heart rate variability (HRV), and body measurements. This is sensitive physiological data.

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