Oura MCP Server

What does “Oura” MCP Server do?

The Oura MCP Server enables AI assistants to securely access, analyze, and visualize health data collected from your Oura Ring through the Model Controller Protocol (MCP). Acting as a bridge between Oura’s API and AI clients, it provides developers and users with structured access to health metrics such as sleep, readiness, activity, and more. The server supports customizable queries, pre-defined prompt templates for common health analysis tasks, and automatic data visualization capabilities. By leveraging this MCP server, AI assistants can perform health trend analysis, generate reports, and surface insightful correlations—empowering developers to build richer, more informative health and wellness experiences.

List of Prompts

• Sleep Data Analysis: Template to retrieve and explain sleep data for a given period.
• Correlate Meals with Readiness: Analyze how meals or nutrition data affect readiness scores.
• Stress vs. Weekday Comparison: Compare stress levels between workdays and weekends.
• Heart Rate During Sleep Analysis: Fetch and analyze heart rate data during sleep, with optional filters (e.g., alcohol consumption).
• Visualize Sleep Efficiency Trends: Create charts showing trends in sleep efficiency or other metrics.
• Compare Readiness Scores: Visualization template comparing readiness after different events (e.g., meals).

List of Resources

• Sleep Metrics: Access to Oura Ring sleep data, including stages, duration, efficiency, and custom tags.
• Readiness Scores: Exposure of readiness scores and their contributing factors.
• Activity Data: Retrieval of daily and weekly activity metrics from Oura.
• Heart Rate Variability (HRV): Detailed HRV data for analysis and visualization.

List of Tools

No explicit list of tools in server.py or similar file is available in the provided repository contents.

Use Cases of this MCP Server

• Personal Sleep Analysis: Developers can build assistants that fetch and interpret users’ sleep patterns, providing actionable insights and visualizations.
• Meal and Readiness Correlation: Enables exploration of how dietary habits impact readiness and overall well-being, supporting personalized health recommendations.
• Stress and Lifestyle Comparison: Facilitates analysis of stress trends across different days (e.g., workdays vs. weekends) for lifestyle optimization.
• Data Visualization for Health Trends: Allows users to generate charts and graphs of Oura Ring data—helpful for coaching, reporting, or personal tracking.
• Custom Health Queries: Supports advanced, user-specific queries (e.g., heart rate during sleep after alcohol consumption) for nuanced health investigation.

How to set it up

Windsurf

1. Ensure Node.js v18+ is installed.
2. Obtain your Oura Personal Access Token and add it to a .env file as OURA_TOKEN=your_personal_access_token.
3. Add the Oura MCP Server package to your configuration:
4. Edit the Windsurf configuration file:

{
  "mcpServers": {
    "oura": {
      "command": "npx",
      "args": ["@oura/mcp-server@latest"]
    }
  }
}

5. Save and restart Windsurf.
6. Verify the MCP server is running and accessible.

Securing API Keys (Windsurf)

{
  "mcpServers": {
    "oura": {
      "command": "npx",
      "args": ["@oura/mcp-server@latest"],
      "env": {
        "OURA_TOKEN": "${OURA_TOKEN}"
      },
      "inputs": {
        "OURA_TOKEN": "your_personal_access_token"
      }
    }
  }
}

Claude

1. Install Node.js v18+.
2. Set up your .env file with OURA_TOKEN.
3. Add the Oura MCP Server to the Claude configuration:

{
  "mcpServers": {
    "oura": {
      "command": "npx",
      "args": ["@oura/mcp-server@latest"]
    }
  }
}

4. Save, restart Claude, and confirm successful connection.

Securing API Keys (Claude)

{
  "mcpServers": {
    "oura": {
      "command": "npx",
      "args": ["@oura/mcp-server@latest"],
      "env": {
        "OURA_TOKEN": "${OURA_TOKEN}"
      }
    }
  }
}

Cursor

1. Confirm Node.js v18+ is installed.
2. Acquire your Oura Personal Access Token and store it in .env.
3. Update the MCP server list in Cursor:

{
  "mcpServers": {
    "oura": {
      "command": "npx",
      "args": ["@oura/mcp-server@latest"]
    }
  }
}

4. Save the configuration and restart Cursor.

Securing API Keys (Cursor)

{
  "mcpServers": {
    "oura": {
      "command": "npx",
      "args": ["@oura/mcp-server@latest"],
      "env": {
        "OURA_TOKEN": "${OURA_TOKEN}"
      }
    }
  }
}

Cline

1. Install Node.js v18 or above.
2. Place your Oura Personal Access Token in a .env file.
3. Add/update the MCP server entry in your Cline configuration:

{
  "mcpServers": {
    "oura": {
      "command": "npx",
      "args": ["@oura/mcp-server@latest"]
    }
  }
}

4. Save changes, restart Cline, and test the setup.

Securing API Keys (Cline)

{
  "mcpServers": {
    "oura": {
      "command": "npx",
      "args": ["@oura/mcp-server@latest"],
      "env": {
        "OURA_TOKEN": "${OURA_TOKEN}"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "oura": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “oura” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the above, the Oura MCP Server covers most required MCP primitives and setup details. However, the absence of explicit tool definitions and sampling/root support documentation limits its completeness as a general-purpose MCP implementation. Still, it offers strong health/tracking features for Oura users.

MCP Score

Our rating: 5/10.
While the server provides good documentation, prompt templates, resource exposure, and setup guidance, it is missing open-source licensing, explicit tools, and sampling/root support, which are important for a well-rounded MCP server. It is suitable for personal health data analysis but not a general MCP showcase.