How to Use the WHOOP MCP in Claude Code

Q: What's the best way to get WHOOP recovery data using Claude Code?

Use getrecovery and specify your start and end dates. The output streams directly to standard out, allowing you to pipe it into tools like jq for immediate JSON parsing in your pipeline.

Q: Does WHOOP support body metric tracking when using Claude Code?

Yes. You can call getbodymeasurement in your terminal scripts. The data streams out, letting you validate physical metrics alongside activity logs from a specific workout ID.

Build health metric pipelines from your terminal using Claude Code.

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 Claude Code

Create your Vinkius account to connect WHOOP to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Batch WHOOP Data Export with the MCP Server

Claude Code runs in the terminal, perfect for CI/CD. Use `claude mcp` to execute commands that call `get_workouts`, specifying a date range filter directly in your script. The output streams raw JSON data you can pipe into other tools. This allows you to pull huge amounts of historical WHOOP activity data and process it immediately, writing the results to a file for later analysis.

System Check and Profile Verification with Claude Code

Before anything else, run `get_profile` using your AI client. This verifies authentication and gets your user ID via the MCP Server. It's always smart to check this first in a script so you know your connection is working. Once verified, you can then call other endpoints like `get_recovery`, knowing your credentials are sound for the duration of the pipeline run.

Single Record Deep Dive using Claude Code

Sometimes you only need one piece of data. You can use `get_sleep_by_id` to fetch a specific sleep record by ID, including full stages and respiratory rate in the terminal output. This is great for scripting checks. Similarly, fetching a single workout with `get_workout` lets your shell script confirm if mandatory fields, like GPS data or strain score, are present for that day.

Setup guide

Set up WHOOP MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see whoop-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest WHOOP transactions." It will automatically discover and invoke the available WHOOP tools.

Terminal

claude mcp add --transport http whoop-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the WHOOP MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "whoop-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

You write a script that calls the MCP Server endpoints. For example, to check all workouts over a month, you pipe a command invoking `get_workouts` with the required date range.

Use `get_recovery` and specify your start and end dates. The output streams directly to standard out, allowing you to pipe it into tools like `jq` for immediate JSON parsing in your pipeline.

You can check system status by first running the profile tool. This confirms connectivity and gives you a user ID, which is vital for any robust CLI script interacting with the MCP Server.

Yes. You can call `get_body_measurement` in your terminal scripts. The data streams out, letting you validate physical metrics alongside activity logs from a specific workout ID.

The server handles sensitive biometrics like sleep duration and heart rate variability (HRV). All calls, especially those retrieving historical `get_sleep` records, are fully logged via the MCP Server.

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