Oura MCP Server
This server provides language models with access to Oura ring health data through the Model Context Protocol (MCP). It enables querying of sleep, readiness, and resilience metrics either for custom date ranges (using ISO format YYYY-MM-DD) or for the current day.
Available Tools:
get_sleep_data/get_today_sleep_data- Retrieve sleep scores and metricsget_readiness_data/get_today_readiness_data- Access readiness scores and contributing factorsget_resilience_data/get_today_resilience_data- Get resilience scores and metrics
Key Features:
Natural language interaction for conversational queries
Flexible date range queries for historical data analysis
Quick access to current day's data without specifying dates
Clear error handling for invalid dates, authentication issues, and network problems
Compatible with Claude Desktop and other MCP-compatible applications
Click on "Deploy 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 Serverwhat's my sleep score for today?"
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.
Oura MCP Server
简体中文 | English | 한국어
A Model Context Protocol (MCP) server that provides access to the Oura API. It allows language models to query sleep, readiness, and resilience data from Oura API.
All Documents
Call for translators! We're looking for translators to help translate this spec for everyone!
Read our documentation in the following languages:
Related MCP server: Oura Ring MCP Server
Available Tools
The server exposes the following tools:
Date Range Queries
get_sleep_data(start_date: str, end_date: str): Get sleep data for a specific date rangeget_readiness_data(start_date: str, end_date: str): Get readiness data for a specific date rangeget_resilience_data(start_date: str, end_date: str): Get resilience data for a specific date range
Dates should be provided in ISO format (YYYY-MM-DD).
Today's Data Queries
get_today_sleep_data(): Get sleep data for todayget_today_readiness_data(): Get readiness data for todayget_today_resilience_data(): Get resilience data for today
Usage
You'll need an Oura API token to use this server. You can obtain one by:
Going to the Oura Developer Portal
Creating a Personal Access Token
Claude for Desktop
Update your claude_desktop_config.json (located in ~/Library/Application\ Support/Claude/claude_desktop_config.json on macOS and %APPDATA%/Claude/claude_desktop_config.json on Windows) to include the following
{
"mcpServers": {
"oura": {
"command": "uvx",
"args": ["oura-mcp-server"],
"env": {
"OURA_API_TOKEN": "YOUR_OURA_API_TOKEN"
}
}
}
}Example Queries
Once connected, you can ask Claude questions like:
"What's my sleep score for today?"
"Show me my readiness data for the past week"
"How was my sleep from January 1st to January 7th?"
"What's my resilience score today?"
Error Handling
The server provides human-readable error messages for common issues:
Invalid date formats
API authentication errors
Network connectivity problems
License
This project is licensed under the MIT License - see the LICENSE file for details.
Maintainer
Core Contributors
Available Tools
6 toolsget_readiness_dataB
Get readiness data for a specific date range.
Args:
start_date: Start date in ISO format (YYYY-MM-DD)
end_date: End date in ISO format (YYYY-MM-DD)
Returns:
Dictionary containing readiness data
| Name | Required | Description | Default |
|---|---|---|---|
| start_date | Yes | ||
| end_date | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a 'Get' operation which implies read-only, but doesn't mention authentication requirements, rate limits, error conditions, or what 'readiness data' actually contains. The return format is vaguely described as a 'Dictionary' without structure details.
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 efficiently structured with a clear purpose statement followed by well-organized Args and Returns sections. Every sentence serves a purpose with zero wasted words.
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?
For a 2-parameter read operation with no output schema, the description covers the basic purpose and parameter formats adequately. However, it lacks details about what 'readiness data' contains, how results are structured, and doesn't differentiate from sibling tools, leaving gaps in contextual understanding.
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 description adds significant value beyond the schema, which has 0% description coverage. It specifies the date format (ISO format YYYY-MM-DD) and clarifies that these are start and end dates for a range. This compensates well for the schema's lack of descriptions.
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 tool's purpose with a specific verb ('Get') and resource ('readiness data'), and specifies a date range constraint. However, it doesn't differentiate from sibling tools like 'get_today_readiness_data' which presumably serves a similar purpose for today's data only.
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 provides no guidance on when to use this tool versus alternatives like 'get_today_readiness_data' or other sibling tools. It mentions a date range but doesn't explain when date-range queries are appropriate versus single-day queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_resilience_dataB
Get resilience data for a specific date range.
Args:
start_date: Start date in ISO format (YYYY-MM-DD)
end_date: End date in ISO format (YYYY-MM-DD)
Returns:
Dictionary containing resilience data
| Name | Required | Description | Default |
|---|---|---|---|
| start_date | Yes | ||
| end_date | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states this is a read operation ('Get'), but doesn't mention authentication requirements, rate limits, error conditions, or what 'resilience data' actually contains. The return format description ('Dictionary containing resilience data') is too vague to be helpful.
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 appropriately sized and well-structured with clear sections (Args, Returns). Each sentence adds value, though the return description could be more specific. It's front-loaded with the core purpose statement.
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's moderate complexity (2 required parameters, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose and parameters but lacks details about what resilience data includes, how results are structured, or behavioral constraints. The absence of output schema means the return description should be more informative.
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 description adds significant value beyond the input schema, which has 0% description coverage. It specifies that both parameters are dates in ISO format (YYYY-MM-DD), clarifies they're required, and explains their purpose (defining a date range). This fully compensates for the schema's lack of descriptions.
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 tool's purpose with a specific verb ('Get') and resource ('resilience data'), and specifies the date range scope. However, it doesn't differentiate from sibling tools like 'get_today_resilience_data' or explain what distinguishes resilience data from readiness or sleep data.
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 provides no guidance on when to use this tool versus alternatives like 'get_today_resilience_data' (which presumably fetches today's data without date parameters) or other sibling tools. There's no mention of prerequisites, constraints, or comparative use cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_sleep_dataB
Get sleep data for a specific date range.
Args:
start_date: Start date in ISO format (YYYY-MM-DD)
end_date: End date in ISO format (YYYY-MM-DD)
Returns:
Dictionary containing sleep data
| Name | Required | Description | Default |
|---|---|---|---|
| start_date | Yes | ||
| end_date | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states the tool 'Get[s] sleep data' which implies a read-only operation, but doesn't disclose behavioral traits like authentication requirements, rate limits, data format details, or error handling. The description is minimal and doesn't add meaningful context beyond the basic operation.
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 appropriately sized and front-loaded with the main purpose in the first sentence. The 'Args' and 'Returns' sections are structured but slightly redundant since the schema already defines parameters. Every sentence earns its place by clarifying parameter formats and return type, though it could be more concise by integrating information.
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's moderate complexity (2 parameters, no annotations, no output schema), the description is minimally complete. It covers the purpose and parameters adequately but lacks details on return value structure, error cases, or integration with sibling tools. Without an output schema, the 'Returns' statement is vague ('Dictionary containing sleep data'), leaving gaps in understanding the response.
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?
Schema description coverage is 0%, so the description must compensate. It provides clear semantics for both parameters: 'start_date' and 'end_date' are explained with format ('ISO format YYYY-MM-DD') and purpose. Since there are only 2 parameters and both are fully documented in the description, this effectively compensates for the schema gap. The baseline would be 3 with high coverage, but here the description adds significant value.
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 tool's purpose with a specific verb ('Get') and resource ('sleep data'), and specifies the scope ('for a specific date range'). It distinguishes from siblings like 'get_today_sleep_data' by indicating date range capability rather than just today's data. However, it doesn't explicitly differentiate from other siblings like 'get_readiness_data' or 'get_resilience_data' beyond the resource type.
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 implies usage context through the date range requirement, suggesting it's for historical data retrieval. It doesn't provide explicit guidance on when to use this tool versus alternatives like 'get_today_sleep_data' for current data, or when not to use it. The context is clear but lacks specific alternatives or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_today_readiness_dataB
Get readiness data for today.
Returns:
Dictionary containing readiness data for today
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
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 behavioral disclosure. It states the tool 'Returns: Dictionary containing readiness data for today,' which hints at output format but lacks details on data structure, error handling, rate limits, authentication needs, or side effects. For a tool with zero annotation coverage, this is insufficient.
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 concise and front-loaded, with the core purpose stated first ('Get readiness data for today.') and a brief return note. Both sentences earn their place by clarifying scope and output. However, it could be slightly more structured (e.g., separating usage notes).
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's simplicity (0 parameters, no output schema, no annotations), the description is incomplete. It lacks context on data format, error cases, or how it differs from siblings. Without annotations or output schema, the description should provide more behavioral and usage details to be fully helpful.
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 tool has 0 parameters, and schema description coverage is 100% (though trivial). The description doesn't need to add parameter semantics, as there are none to explain. A baseline of 4 is appropriate for zero-parameter tools, as no compensation is required.
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 tool's purpose: 'Get readiness data for today.' It specifies the verb ('Get') and resource ('readiness data') with temporal scope ('for today'). However, it doesn't explicitly differentiate from sibling tools like 'get_readiness_data' (which likely lacks the 'today' filter) or 'get_today_resilience_data' (which targets a different data type).
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 provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'get_readiness_data' (for broader date ranges) or 'get_today_resilience_data' (for different metrics), nor does it specify prerequisites, exclusions, or contextual triggers for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_today_resilience_dataC
Get resilience data for today.
Returns:
Dictionary containing resilience data for today
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool returns a dictionary but lacks details on behavioral traits such as data freshness, error handling, authentication needs, or rate limits. For a read operation with zero annotation coverage, this is inadequate.
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 brief and front-loaded with the main purpose, but the 'Returns:' section is redundant as it restates the purpose without adding value. It could be more concise by omitting the second sentence or integrating it better.
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 no annotations and no output schema, the description is incomplete. It lacks details on the return format (e.g., structure of the dictionary), error conditions, or dependencies. For a tool with siblings and no structured support, more context is needed to be fully helpful.
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 tool has 0 parameters with 100% schema description coverage, so no parameter information is needed. The description doesn't add param semantics beyond the schema, but since there are no parameters, a baseline of 4 is appropriate as it doesn't need to compensate for gaps.
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 verb ('Get') and resource ('resilience data for today'), making the purpose understandable. It distinguishes from the sibling 'get_resilience_data' by specifying 'today', but doesn't explicitly differentiate from 'get_today_readiness_data' or 'get_today_sleep_data' beyond the resource type.
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?
No guidance is provided on when to use this tool versus alternatives like 'get_resilience_data' (which might fetch broader date ranges) or other 'today' tools for different data types. The description implies usage for today's resilience data but offers no explicit context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_today_sleep_dataB
Get sleep data for today.
Returns:
Dictionary containing sleep data for today
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states it 'Returns: Dictionary containing sleep data for today', which adds some behavioral context about the output format. However, it lacks details on error handling, data freshness, authentication needs, or rate limits, which are important for a data-fetching tool.
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 with two short sentences, front-loading the purpose and then specifying the return format. There's no wasted text, though the structure could be slightly improved by integrating the return info more seamlessly.
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's simplicity (0 parameters, no output schema, no annotations), the description is minimally adequate. It covers the purpose and return format, but lacks context on data sources, update frequency, or error cases, which could help the agent use it more effectively.
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 tool has 0 parameters, and schema description coverage is 100%, so no parameter documentation is needed. The description doesn't add parameter info, but that's appropriate here. A baseline of 4 is applied as it adequately addresses the lack of parameters.
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 verb ('Get') and resource ('sleep data for today'), making the purpose immediately understandable. It distinguishes from the sibling 'get_sleep_data' by specifying 'today', though it doesn't explicitly contrast with other siblings like 'get_today_readiness_data'.
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?
No guidance is provided on when to use this tool versus alternatives. It doesn't mention its sibling tools (e.g., 'get_sleep_data' for other date ranges or 'get_today_readiness_data' for different data types), leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
v1.0.0- Changed
get_readiness_data1 field changed- added
Input schema / titleAdded value: +"get_readiness_dataArguments"
- Changed
get_resilience_data1 field changed- added
Input schema / titleAdded value: +"get_resilience_dataArguments"
- Changed
get_sleep_data1 field changed- added
Input schema / titleAdded value: +"get_sleep_dataArguments"
- Changed
get_today_readiness_data1 field changed- added
Input schema / titleAdded value: +"get_today_readiness_dataArguments"
- Changed
get_today_resilience_data1 field changed- added
Input schema / titleAdded value: +"get_today_resilience_dataArguments"
- Changed
get_today_sleep_data1 field changed- added
Input schema / titleAdded value: +"get_today_sleep_dataArguments"
6 tool updates
- First observed
get_readiness_data - First observed
get_resilience_data - First observed
get_sleep_data - First observed
get_today_readiness_data - First observed
get_today_resilience_data - First observed
get_today_sleep_data
TDQS
Scored across 6 tools
The tools are clearly organized around three data types (readiness, resilience, sleep) with two temporal variants (date range vs. today), making them mostly distinct. However, the 'get_today_*' tools could be seen as overlapping with the date-range versions if an agent specifies today's date, though their dedicated purpose reduces confusion.
All tools follow a consistent verb_noun pattern with 'get_' prefix, and the naming is systematic across data types and temporal variants (e.g., get_readiness_data, get_today_readiness_data). There are no deviations in style or convention.
With 6 tools, this is well-scoped for an Oura data server, covering three key metrics with both historical and current-day access. Each tool serves a clear purpose without redundancy, fitting typical expectations for such a domain.
The server covers the core read operations for readiness, resilience, and sleep data with both date-range and today-specific queries, which is appropriate for a fitness/health tracking domain. A minor gap is the lack of write or update tools (e.g., to set goals or log activities), but as a read-only data retrieval surface, it is largely complete.
Maintenance
Related MCP Connectors
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…
- freddyOAuthcoach.freddy
Connect your wearables, rings and training apps, then ask your AI about your own health data.
Multi-tenant hosted MCP server for Oura Ring — 21 read-only tools, OAuth per user.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to access and analyze Oura Ring health data including sleep, readiness, activity, and stress metrics. Supports customizable queries, correlation analysis, and visualization capabilities for comprehensive health insights.-
- AlicenseNot gradedqualityDmaintenanceEnables access to Oura Ring health data including sleep patterns, activity metrics, readiness scores, heart rate, workouts, and stress measurements with AI-powered analysis and personalized recommendations.67 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides LLMs with access to Oura Ring health data including sleep metrics, activity tracking, heart rate, readiness scores, and other wellness insights through the Oura API v2.MIT
- AlicenseCqualityDmaintenanceEnables AI assistants to access and analyze Oura Ring health data, including sleep, readiness, and activity metrics, with support for visualization and correlation analysis.12 npm15MIT