How to Use the WHOOP MCP in LlamaIndex

Q: How does LlamaIndex handle querying historical WHOOP workout data?

You query the indexed results from getworkouts. The system doesn't just return a list; it synthesizes an answer based on the context of your overall knowledge base and the specified date range.

Q: Can LlamaIndex ground answers using WHOOP profile data?

Absolutely. After calling getprofile, you can index that user ID information along with other metrics, ensuring any answer referencing your account is accurate and tied to the live API data.

Q: What happens when I ask LlamaIndex about WHOOP recovery changes?

The system looks at indexed results from getrecovery across date ranges. It combines that with sleep metrics from getsleep to give you a nuanced answer, rather than just dumping raw scores.

Q: How do I ensure LlamaIndex uses recent WHOOP data?

You must pass date ranges to the respective tools (getworkouts, getsleep) so the fresh information is pulled and subsequently indexed into your vector store for accurate querying.

Build knowledge-augmented WHOOP apps with LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect WHOOP to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Indexing and Querying Whole WHOOP Cycles with LlamaIndex

The `get_cycles` tool fetches full 24-hour data points—sleep, recovery, strain, heart rate. You can index these outputs into a vector store. Later, your application queries this knowledge base to answer questions like, 'What was my average sleep quality in Q3?' This means the raw data from `get_cycles` becomes part of your searchable corpus. When a user asks about their fitness trends, LlamaIndex grounds the answer using the actual API results.

Retrieving WHOOP Workout Details via MCP Server

Use `get_workouts` to pull specific workout data by date range or use `get_workout` for a single ID. Indexing this data allows you to build an internal knowledge graph of user activity. If your RAG application needs to compare a specific training session against general recovery trends, it can retrieve the `get_body_measurement` results and combine them with the workout metrics.

Handling WHOOP Sleep Records with LlamaIndex

The `get_sleep_by_id` tool gives you full sleep stages, disturbances, and respiratory rates. By indexing these detailed records, your agent can answer highly specific questions about poor sleep nights. When a user asks, 'Why was my recovery low last week?', the index searches through both the sleep data (`get_sleep`) and the cycle data (`get_cycle_recovery`) to provide a comprehensive, source-backed explanation.

Setup guide

Set up WHOOP MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all WHOOP MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to WHOOP tools.",
)
response = await agent.run("List recent WHOOP data")

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 LlamaIndex

You query the indexed results from `get_workouts`. The system doesn't just return a list; it synthesizes an answer based on the context of your overall knowledge base and the specified date range.

Absolutely. After calling `get_profile`, you can index that user ID information along with other metrics, ensuring any answer referencing your account is accurate and tied to the live API data.

The system looks at indexed results from `get_recovery` across date ranges. It combines that with sleep metrics from `get_sleep` to give you a nuanced answer, rather than just dumping raw scores.

Yes. When querying, the system is aware of which data types are being used. For instance, it can pinpoint specific `body_measurement` results that were indexed.

You must pass date ranges to the respective tools (`get_workouts`, `get_sleep`) so the fresh information is pulled and subsequently indexed into your vector store for accurate querying.

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