How do I get an Oura Personal Access Token?

Log in to your Oura account at [**cloud.ouraring.com**](https://cloud.ouraring.com/oauth2/authorize), create a personal access token in your account settings. The token gives access to your sleep, activity, readiness and health data.

What health data is available?

Sleep (score, stages, efficiency), Activity (steps, calories, MET), Readiness (score, HRV, RHR, temperature), Tags (mood, energy, behaviors), Workouts (type, duration, HR zones) and Heart Rate (5-min samples).

How far back can I access data?

You can access all historical data recorded by your Oura Ring. Use start_date and end_date parameters to filter results. Data is paginated with a nextToken for large date ranges.

Oura MCP Server for OpenAI Agents SDK 7 tools — connect in under 2 minutes

Name: Oura
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 7 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Oura through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

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 agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Oura Assistant",
            instructions=(
                "You help users interact with Oura. "
                "You have access to 7 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Oura"
        )
        print(result.final_output)

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 Oura MCP Server

Connect your Oura Ring to any AI agent and access your personal health data through natural conversation.

The OpenAI Agents SDK auto-discovers all 7 tools from Oura through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Oura, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Sleep — Analyze sleep scores, stages (REM/light/deep/wake), efficiency, latency and timing
Activity — Track daily steps, calories, MET minutes and activity goals
Readiness — Monitor readiness scores, HRV, resting heart rate, body temperature and recovery
Tags — Review your manual entries for mood, energy, behaviors and substances
Workouts — Browse logged workouts with type, duration, calories and heart rate zones
Heart Rate — Access detailed 5-minute heart rate samples and HRV data

The Oura MCP Server exposes 7 tools through the Vinkius. Connect it to OpenAI Agents SDK 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 Oura to OpenAI Agents SDK via MCP

Follow these steps to integrate the Oura MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 7 tools from Oura

Why Use OpenAI Agents SDK with the Oura MCP Server

OpenAI Agents SDK provides unique advantages when paired with Oura through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Oura + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Oura MCP Server delivers measurable value.

Automated workflows: build agents that query Oura, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Oura, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Oura tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Oura to resolve tickets, look up records, and update statuses without human intervention

Oura MCP Tools for OpenAI Agents SDK (7)

These 7 tools become available when you connect Oura to OpenAI Agents SDK via MCP:

get_activity

Supports date range filtering. Get your Oura activity data

get_heart_rate

Returns timestamp, heart rate value and HRV for each sample. Supports date range filtering. Note: This endpoint returns high-frequency data; use narrow date ranges. Get your Oura heart rate data

get_readiness

Supports date range filtering. Get your Oura readiness data

get_sessions

Includes overall scores, sleep metrics, activity data and readiness indicators. Supports date range filtering. Get your Oura session data

get_sleep

Supports date range filtering with start_date and end_date (YYYY-MM-DD). Pagination via nextToken. Get your Oura sleep data

get_tags

). Tags are user-entered data points that correlate with sleep and readiness scores. Supports date range filtering. Get your Oura tags

get_workouts

Workouts can be manually logged or auto-detected by the Oura Ring. Supports date range filtering. Get your Oura workout data

Example Prompts for Oura in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Oura immediately.

"How did I sleep last night?"

"What is my readiness score today?"

"Show me my activity from yesterday."

Troubleshooting Oura MCP Server with OpenAI Agents SDK

Common issues when connecting Oura to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Oura + OpenAI Agents SDK FAQ

Common questions about integrating Oura MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.