How to Use the WHOOP MCP in LangChain

Q: How do I search WHOOP data history using LangChain?

To get historical workout data, call getworkouts and specify a start or end date. If you want to check sleep patterns for that period, follow up by calling getsleep with the same date range parameters.

Q: Can LangChain connect WHOOP recovery scores to workout details?

Yes. You first grab a specific cycle's data using getcyclerecovery. Then, you can fetch associated physical activity records by calling getworkout and comparing the dates.

Q: Does WHOOP track heart rate variability when using LangChain?

Yep. When you call getcyclerecovery, it returns HRV (heart rate variability) directly. This data is one of several core metrics available for a given 24-hour period.

Q: What data does the MCP Server provide regarding WHOOP sleep stages?

The getsleep tool gives you duration and performance percentages, while using getsleepbyid provides a deeper dive into light, deep, REM, and awake stages.

Q: How do I confirm WHOOP connection status with LangChain?

Just use the getprofile tool. It’s the fastest way to verify your authentication is working and grab the user ID needed for all other MCP Server calls.

Build multi-step WHOOP agents using LangChain.

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 LangChain

Create your Vinkius account to connect WHOOP to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Building Complex WHOOP Workflows with LangChain

The `get_cycles` tool lets your agent pull full 24-hour periods of data, including sleep, recovery, strain, and heart rate. You can chain this output: feed the resulting cycle IDs into a subsequent call to `get_recovery` or `get_sleep` for detailed analysis. This means you aren't just fetching raw records; your agent builds an entire narrative. It decides if it needs to check body measurements via `get_body_measurement` first, then pull the workout details using `get_workout`, and finally compile a full health report.

Querying WHOOP Data Streams with MCP Server

Need to know exactly when a user slept? Use `get_sleep` to grab sleep records across date ranges, then pass the resulting Sleep IDs into `get_sleep_by_id`. This gives you granular details like respiratory rate and specific disturbances. Your agent can handle complex queries. If it needs recovery data for a range of dates, it uses `get_recovery`, which supports filtering. Then, if it also requires strain metrics, the chain calls `get_workouts` next.

Analyzing WHOOP Profile and Metrics with LangChain

The `get_profile` tool verifies your authentication quickly, giving you a user ID necessary for other endpoints. You can use this initial step to confirm connectivity before running expensive data calls. Once authenticated, an agent can pull historical data points by date range—like calling `get_workouts` or `get_body_measurement`. The results from one tool call become the input parameters for the next tool in your sequence.

Setup guide

Set up WHOOP MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes WHOOP tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "whoop-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent WHOOP transactions"
    })
    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 LangChain

To get historical workout data, call `get_workouts` and specify a start or end date. If you want to check sleep patterns for that period, follow up by calling `get_sleep` with the same date range parameters.

Yes. You first grab a specific cycle's data using `get_cycle_recovery`. Then, you can fetch associated physical activity records by calling `get_workout` and comparing the dates.

Yep. When you call `get_cycle_recovery`, it returns HRV (heart rate variability) directly. This data is one of several core metrics available for a given 24-hour period.

The `get_sleep` tool gives you duration and performance percentages, while using `get_sleep_by_id` provides a deeper dive into light, deep, REM, and awake stages.

Just use the `get_profile` tool. It’s the fastest way to verify your authentication is working and grab the user ID needed for all other MCP Server calls.

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