Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@oura-mcp-server Show my sleep data for last night"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This server enables AI assistants to access and analyze your Oura Ring data through the Model Controller Protocol (MCP). It provides a structured way to fetch and understand your health metrics.
Secure access to your Oura Ring data
Pre-defined prompts for common health analysis tasks
Customizable queries for specific health insights
Support for analyzing correlations between different metrics
Proper handling of time units and calculation guidelines
Visualization capabilities for health metrics
Related MCP server: Oura MCP Server
Node.js v18 or higher
An Oura Ring account with Personal Access Token
Clone the repository:
git clone https://github.com/yourusername/oura-mcp-server.git
cd oura-mcp-serverInstall dependencies:
npm installCreate a .env file in the root directory with your Oura API token:
OURA_TOKEN=your_personal_access_token_hereBuild the project:
npm run buildStart the server:
npm startGo to the Oura Developer website
Log in with your Oura account
Create a new Personal Access Token
Copy the token to your .env file
You can ask Claude things like:
"Show me my sleep data for the last week and explain what it means"
"Analyze how my meals affect my readiness scores"
"Compare my stress levels on workdays versus weekends"
"Show me my heart rate during sleep for nights when I had alcohol"
"Visualize my sleep efficiency trends for the past month" (Claude will generate charts!)
"Create a visualization comparing my readiness scores after different meals"
Claude can create visual charts to help you understand your health data. Simply ask Claude to "visualize" or "create a chart" of specific metrics. For example:
"Visualize my sleep stages over the past week"
"Create a chart showing the correlation between HRV and sleep quality"
"Make a bar graph comparing my activity scores by day of week"
"Plot my resting heart rate against stress levels"
This server follows these key guidelines:
All duration fields are in seconds and converted to hours/minutes for display
Sleep percentages are calculated using total_sleep_duration as denominator
Sleep efficiency is calculated as (total_sleep_duration / time_in_bed * 100)
Custom tags contain meal information in the comment field
Contributions are welcome! Please feel free to submit a Pull Request.
Fetch data from Oura Ring API endpoints
| Name | Required | Description | Default |
|---|---|---|---|
| endpoint | Yes | The Oura API endpoint to fetch data from | |
| startDate | No | Start date in YYYY-MM-DD format | |
| endDate | No | End date in YYYY-MM-DD format | |
| startDateTime | No | Start datetime in ISO format with timezone (for heartrate endpoint) | |
| endDateTime | No | End datetime in ISO format with timezone (for heartrate endpoint) | |
| sleepPeriod | No | Whether to filter heart rate data to sleep periods only (requires additional sleep data fetch) | |
| tagName | No | Optional filter for specific tag name or keyword in comment |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of disclosing behavioral traits. The description only implies a read operation ('Fetch') but does not address authentication, rate limits, error handling, or whether data is read-only. This is insufficient for an agent to understand the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence, 7 words). While there is no wasted text, it is under-specified for a tool with 7 parameters. A slightly longer description could add valuable context without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 7 parameters and no output schema, the description should provide more context about the endpoints, return format, or usage scenarios. Currently it is too minimal to be considered complete for effective agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of parameters with descriptions, so the baseline is 3. The tool description does not add any additional meaning or context for the parameters beyond what the schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Fetch') and the resource ('data from Oura Ring API endpoints'). It is not a tautology and provides a specific verb and resource, though it remains generic without distinguishing between endpoints. With no sibling tools, a score of 4 is appropriate.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description offers no guidance on when to use this tool versus alternatives, no exclusions, and no context about prerequisites or ideal scenarios. It simply states what the tool does without any usage instructions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0oura-fetchWith only one tool, there is no possibility of confusion or overlap. The purpose is clear.
The single tool name 'oura-fetch' follows a clear verb_noun pattern, consistent with itself.
A single generic fetch tool is far too few for the broad Oura Ring API domain, which has many endpoints for different data types.
The tool surface is severely incomplete: it provides only a raw fetch without specific operations for sleep, activity, readiness, etc., leaving agents without necessary capabilities.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Connect your wearables, rings and training apps, then ask your AI about your own health data.
Connect your Oura Ring account securely in minutes. Enable authorized access to your sleep, activi…
Connect your Oura Ring account and enable access to your wellness data in apps and automations. In…
Your WHOOP data in the assistant, read-only: recovery, sleep, strain, workouts, cycles and body meas
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/rajvirtual/oura-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
