How to Use the WHOOP MCP in Pydantic AI

Q: How do I check WHOOP data using pydantic-ai?

Start by hitting getprofile to verify the user ID. After that, you can query specific metrics like sleep stages with getsleepbyid, which returns full detail on disturbances and respiratory rate.

Q: Can the pydantic-ai handle large data requests for WHOOP?

Yes. Tools like getrecovery support date range filtering and pagination, meaning you can fetch continuous streams of health records without failure.

Q: What is the most detailed view of sleep available with pydantic-ai?

Use getsleepbyid. It provides maximum detail on sleep stages, disturbances, and respiratory rate—stuff you need for serious analysis.

Validate WHOOP health data structures with Pydantic AI's robust MCP Server integration.

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 Pydantic AI

Create your Vinkius account to connect WHOOP to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Retrieve cycle status via pydantic-ai

When you pull a user's recovery profile, the `get_cycle_recovery` tool gives clean data on recovery score, resting heart rate, and HRV. This output is validated against Pydantic models. Want to know how deep sleep was? Use `get_cycle_sleep`. It supplies duration, stages (REM/deep), disturbances, and the overall performance percentage for a specific 24-hour period.

Build workout logs with pydantic-ai

Using `get_workout` lets you get precise details—strain score, duration, heart rate zones, and calories burned—for one exercise. Since the output is typed, you never risk bad data. For an agent needing a history, `get_workouts` handles fetching multiple WHOOP workout records over time, with pagination support for 25 results.

Get general health summaries using the MCP Server

Need to check body metrics? The `get_body_measurement` tool pulls this data. It’s useful alongside core WHOOP numbers because it adds context. For broad trends, query `get_cycles`. This single tool grabs a mix of sleep, recovery, strain, and heart rate metrics for any given date range.

Setup guide

Set up WHOOP MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "whoop-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to WHOOP tools.",
)

result = await agent.run("List recent WHOOP transactions")
print(result.output)

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 Pydantic AI

Start by hitting `get_profile` to verify the user ID. After that, you can query specific metrics like sleep stages with `get_sleep_by_id`, which returns full detail on disturbances and respiratory rate.

The MCP Server supports everything from daily cycle reports (`get_cycles`) to body measurements via `get_body_measurement`, making it a central source for fitness agents.

Yes. Tools like `get_recovery` support date range filtering and pagination, meaning you can fetch continuous streams of health records without failure.

Use `get_sleep_by_id`. It provides maximum detail on sleep stages, disturbances, and respiratory rate—stuff you need for serious analysis.

The server touches granular physiological measurements like HRV, recovery score, specific body metrics, and detailed sleep stages. This is considered high-value health information.

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