How do I get WHOOP API credentials?

Visit [**developer.whoop.com**](https://developer.whoop.com/), create an app to get a Client ID and Client Secret. Then complete the OAuth2 flow to obtain an Access Token. All three are required for API access.

What is a WHOOP cycle?

A WHOOP cycle represents a 24-hour period combining your sleep, strain and recovery data. Each cycle starts when you wake up and includes the previous night's sleep, the day's strain, and your recovery score for the next day.

How much historical data can I access?

You can access all historical data recorded by your WHOOP device. Use the start and end date parameters (ISO 8601 format) to filter results. Pagination returns up to 25 records per request; use the nextToken to retrieve more.

Does the API include heart rate data?

Yes! Heart rate data (average and max) is included in the cycle, workout and recovery responses. There's no dedicated heart rate endpoint, but the data is nested within these resources.

WHOOP MCP Server for AutoGen 11 tools — connect in under 2 minutes

Name: WHOOP
Availability: InStock
Author: Vinkius

microsoft.github.io/autogen/docs/tools/mcp-tools

Built by Vinkius GDPR 11 Tools Framework

Microsoft AutoGen enables multi-agent conversations where agents negotiate, delegate, and execute tasks collaboratively. Add WHOOP as an MCP tool provider through the Vinkius and every agent in the group can access live data and take action.

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 autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with McpWorkbench(
        server_params={"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"},
        transport="streamable_http",
    ) as workbench:
        tools = await workbench.list_tools()
        agent = AssistantAgent(
            name="whoop_agent",
            tools=tools,
            system_message=(
                "You help users with WHOOP. "
                "11 tools available."
            ),
        )
        print(f"Agent ready with {len(tools)} tools")

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 WHOOP MCP Server

Connect your WHOOP account to any AI agent and access your personal health data through natural conversation.

AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use WHOOP tools. Connect 11 tools through the Vinkius and assign role-based access — a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.

What you can do

Profile — View your WHOOP profile and body measurements (height, weight, max HR)
Cycles — Browse your 24-hour WHOOP cycles combining sleep, strain and recovery
Sleep — Analyze sleep data with stages (light, deep, REM), duration and performance
Recovery — Track recovery scores, HRV, resting heart rate and sleep balance
Workouts — Review workout data with strain, heart rate zones, duration and calories
Pagination — Navigate through historical data with date ranges and pagination tokens

The WHOOP MCP Server exposes 11 tools through the Vinkius. Connect it to AutoGen 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 WHOOP to AutoGen via MCP

Follow these steps to integrate the WHOOP MCP Server with AutoGen.

Install AutoGen

Run pip install "autogen-ext[mcp]"

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Integrate into workflow

Use the agent in your AutoGen multi-agent orchestration

Explore tools

The workbench discovers 11 tools from WHOOP automatically

Why Use AutoGen with the WHOOP MCP Server

AutoGen provides unique advantages when paired with WHOOP through the Model Context Protocol.

Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use WHOOP tools to solve complex tasks

Role-based architecture lets you assign WHOOP tool access to specific agents — a data analyst queries while a reviewer validates

Human-in-the-loop support: agents can pause for human approval before executing sensitive WHOOP tool calls

Code execution sandbox: AutoGen agents can write and run code that processes WHOOP tool responses in an isolated environment

WHOOP + AutoGen Use Cases

Practical scenarios where AutoGen combined with the WHOOP MCP Server delivers measurable value.

Collaborative analysis: one agent queries WHOOP while another validates results and a third generates the final report

Automated review pipelines: a researcher agent fetches data from WHOOP, a critic agent evaluates quality, and a writer produces the output

Interactive planning: agents negotiate task allocation using WHOOP data to make informed decisions about resource distribution

Code generation with live data: an AutoGen coder agent writes scripts that process WHOOP responses in a sandboxed execution environment

WHOOP MCP Tools for AutoGen (11)

These 11 tools become available when you connect WHOOP to AutoGen via MCP:

get_body_measurement

Useful for tracking physical metrics alongside your WHOOP data. Get your body measurement data

get_cycle

Includes sleep, recovery, strain and heart rate metrics for that 24-hour period. Get a specific WHOOP cycle by ID

get_cycle_recovery

Includes recovery score, resting heart rate, HRV (heart rate variability), sleep balance and strain balance. Get recovery data for a specific WHOOP cycle

get_cycle_sleep

Includes sleep duration, stages (light, deep, REM, awake), disturbances and sleep performance percentage. Get sleep data for a specific WHOOP cycle

get_cycles

Cycles represent 24-hour periods of recovery and strain data. Each cycle includes sleep, recovery, strain and heart rate metrics. Supports date range filtering with start/end in ISO 8601 format. Pagination: max 25 results, use nextToken for more. Get your WHOOP cycle data

get_profile

Use this to verify your authentication is working and get your user ID for other endpoints. Get your WHOOP profile info

get_recovery

Supports date range filtering. Pagination: max 25 results per request. Get your WHOOP recovery data

get_sleep

Supports date range filtering. Pagination: max 25 results. Get your WHOOP sleep data

get_sleep_by_id

Includes full sleep stages, disturbances, respiratory rate and sleep performance. Get a specific WHOOP sleep record by ID

get_workout

Includes strain score, duration, heart rate zones, calories burned and GPS data if available. Get a specific WHOOP workout by ID

get_workouts

Supports date range filtering. Pagination: max 25 results. Get your WHOOP workout data

Example Prompts for WHOOP in AutoGen

Ready-to-use prompts you can give your AutoGen agent to start working with WHOOP immediately.

"Show me my recovery score from today."

"How did I sleep last night?"

"Show me my workouts from this week."

Troubleshooting WHOOP MCP Server with AutoGen

Common issues when connecting WHOOP to AutoGen through the Vinkius, and how to resolve them.

McpWorkbench not found

Install: pip install "autogen-ext[mcp]"

WHOOP + AutoGen FAQ

Common questions about integrating WHOOP MCP Server with AutoGen.

How does AutoGen connect to MCP servers?

Create an MCP tool adapter and assign it to one or more agents in the group chat. AutoGen agents can then call WHOOP tools during their conversation turns.

Can different agents have different MCP tool access?

Yes. AutoGen's role-based architecture lets you assign specific MCP tools to specific agents, so a querying agent has different capabilities than a reviewing agent.