oura-ring-mcp
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-ring-mcp How was my sleep 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.
Oura MCP Server
An MCP server that connects your Oura Ring to Claude and other AI assistants. Get human-readable insights about your sleep, readiness, and activity—not just raw JSON.
Features
Smart formatting - Durations in hours/minutes, scores with context ("85 - Optimal")
Sleep analysis - Sleep stages, efficiency, HRV, and biometrics
Readiness tracking - Recovery scores and contributor breakdown
Activity data - Steps, calories, and intensity breakdown
Health metrics - Heart rate, SpO2, stress, cardiovascular age
Smart analysis - Anomaly detection, correlations, trend analysis
Tags support - Compare metrics with/without conditions
See example outputs — what Claude returns for sleep, readiness, weekly summaries, and smart analysis
Related MCP server: Oura MCP Server
Quick Start
1. Install
npm install -g oura-ring-mcpOr use directly with npx (no install needed):
npx oura-ring-mcp2. Authenticate with Oura
Option A: Personal Access Token (simpler)
Create a new token
Set
OURA_ACCESS_TOKENin your Claude Desktop config (see below)
Option B: OAuth CLI Flow
Create an OAuth app at developer.ouraring.com
Set Redirect URI to
http://localhost:3000/callback
Run the auth flow:
export OURA_CLIENT_ID=your_client_id export OURA_CLIENT_SECRET=your_client_secret npx oura-ring-mcp authCredentials are saved to
~/.oura-mcp/credentials.json
3. Configure Claude Desktop
Add to claude_desktop_config.json:
With Personal Access Token:
{
"mcpServers": {
"oura": {
"command": "npx",
"args": ["oura-ring-mcp"],
"env": {
"OURA_ACCESS_TOKEN": "your_token_here"
}
}
}
}With OAuth (after running npx oura-ring-mcp auth):
{
"mcpServers": {
"oura": {
"command": "npx",
"args": ["oura-ring-mcp"]
}
}
}The server reads credentials from ~/.oura-mcp/credentials.json. To enable automatic token refresh, add your OAuth credentials:
{
"mcpServers": {
"oura": {
"command": "npx",
"args": ["oura-ring-mcp"],
"env": {
"OURA_CLIENT_ID": "your_client_id",
"OURA_CLIENT_SECRET": "your_client_secret"
}
}
}
}Restart Claude Desktop. Requires Node >=18.
What Can I Ask?
Daily check-ins:
"How did I sleep last night?"
"Am I recovered enough to work out today?"
"What's my body telling me right now?"
Patterns & trends:
"Do I sleep better on weekends?"
"What time should I go to bed for optimal sleep?"
"Is my HRV improving or declining?"
Correlations & insights:
"Does alcohol affect my sleep quality?"
"What predicts my best sleep nights?"
"How does exercise timing affect my recovery?"
Comparisons:
"Compare my sleep this week vs last week"
"How do I sleep after meditation vs without?"
"What changed when I started taking magnesium?"
Anomalies:
"Are there any unusual readings in my data?"
"Why was my readiness so low yesterday?"
"Find days where my metrics were off"
Available Tools
Data Retrieval
Tool | Description |
| Sleep data with stages, efficiency, HR, HRV |
| Daily sleep scores with contributors |
| Readiness scores and recovery metrics |
| Steps, calories, intensity breakdown |
| Workout sessions with type and intensity |
| Meditation and relaxation sessions |
| HR readings throughout the day |
| Stress levels and recovery time |
| Blood oxygen and breathing disturbance |
| User-created tags and notes |
Smart Analysis
Tool | Description |
| Find unusual readings using outlier detection |
| Sleep analysis with trends, patterns, debt |
| Find correlations between health metrics |
| Compare this week vs last week |
| Compare metrics with/without a tag |
| What predicts your good vs poor sleep |
| HRV trend with rolling averages |
Resources
Resource | Description |
| Today's health summary |
| Last 7 days with averages |
| Your 30-day averages and normal ranges |
| 30-day analysis with trends and anomalies |
| Your tags and usage frequency |
Prompts
Prompt | Description |
| Comprehensive weekly health review |
| Identify what leads to your best sleep |
| Should you train hard or rest today? |
| This week vs last week comparison |
| How a specific tag affects your health |
Remote Deployment (Railway)
Deploy the MCP server for remote access. The server proxies OAuth through Oura, so users authenticate directly with their Oura account — no PAT needed.
1. Create an Oura OAuth App
Go to Oura OAuth Applications
Create a new application
Set the Redirect URI to:
https://your-app.railway.app/oauth/callbackNote the Client ID and Client Secret
2. Deploy
# Install Railway CLI
npm install -g @railway/cli
# Login, init, and deploy
railway login
railway init
railway up3. Set Environment Variables
In the Railway dashboard, add:
Variable | Description |
| From your Oura OAuth app |
| From your Oura OAuth app |
|
|
| (Optional) Static bearer token for Claude Desktop ( |
| (Optional) PAT fallback if not using OAuth ( |
Railway automatically sets PORT and RAILWAY_PUBLIC_DOMAIN.
4. Connect from Claude.ai
Use the connector in Claude.ai:
Go to Settings > MCP Connectors > Add
Enter your server URL:
https://your-app.railway.app(without/mcp)Leave OAuth Client ID and Secret empty (dynamic registration handles it)
You'll be redirected to Oura to authorize access to your data
5. Connect from Claude Desktop
For Claude Desktop, use MCP_SECRET + OURA_ACCESS_TOKEN:
{
"mcpServers": {
"oura-remote": {
"url": "https://your-app.railway.app/mcp",
"headers": {
"Authorization": "Bearer your_mcp_secret_here"
}
}
}
}Local Testing
# With Oura OAuth (full flow)
OURA_CLIENT_ID=your_id OURA_CLIENT_SECRET=your_secret pnpm start:http
# With static secret only (requires OURA_ACCESS_TOKEN)
OURA_ACCESS_TOKEN=your_pat MCP_SECRET=test-secret pnpm start:http
# Verify health endpoint
curl http://localhost:3000/health
# Check OAuth metadata (only available when OURA_CLIENT_ID is set)
curl http://localhost:3000/.well-known/oauth-authorization-server
# Test authenticated request (with static secret)
curl -X POST http://localhost:3000/mcp \
-H "Authorization: Bearer test-secret" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"initialize","params":{"capabilities":{}},"id":1}'Contributing
See CLAUDE.md for architecture details and development guidelines.
License
MIT
Available Tools
27 toolsanalyze_adherenceA
Analyze how consistently you wear your Oura ring. Shows daily non-wear time, identifies gaps in data, and calculates adherence percentage. Useful for understanding data quality.
Inputs: days.
analyze_hrv_trendA
Analyze your HRV (Heart Rate Variability) trend over time. HRV is a key indicator of recovery and stress. Shows trend direction, rolling averages, and identifies recovery patterns.
Inputs: days.
analyze_sleep_qualityA
Comprehensive sleep quality analysis over a time period. Shows trends, patterns by day of week, sleep debt, regularity score, and identifies your best/worst sleep days. Great for understanding what affects your sleep.
Inputs: days.
analyze_temperatureB
Analyze body temperature patterns from readiness data. Temperature deviations can indicate illness, menstrual cycle phases, or environmental factors. Shows trends and flags unusual readings.
Inputs: days.
best_sleep_conditionsA
Analyze what conditions are associated with your best sleep nights. Looks at activity levels, workouts, meditation sessions, tags, and day-of-week patterns to identify what predicts good vs poor sleep.
Inputs: days.
compare_conditionsA
Compare a health metric across different conditions. Supports manual tags (alcohol, caffeine) AND auto-tracked conditions: 'workout' (workout days vs rest days), 'high_activity' (high step days), 'meditation' (session days).
Inputs: tag (required), metric (required), days.
compare_periodsA
Compare health metrics between two time periods. Great for answering questions like 'How did I sleep this week vs last week?' or 'Was my HRV better last month?'. Returns side-by-side comparison with percentage changes.
Inputs: period1_start (required), period1_end (required), period2_start (required), period2_end (required), +1 more.
correlate_metricsA
Find correlations between two health metrics. For example, see if your HRV correlates with sleep duration, or if activity affects your readiness. Returns correlation strength, direction, and statistical significance.
Inputs: metric1 (required), metric2 (required), days.
detect_anomaliesA
Detect unusual readings in your health data over a time period. Uses statistical methods (IQR and Z-score) to flag outliers in sleep, HRV, heart rate, and activity. Useful for identifying nights with unusually poor sleep, stress spikes, or other anomalies.
Inputs: days, metrics.
get_activityA
Get daily activity data including steps, calories, and activity breakdown (high/medium/low intensity). Use this to analyze movement and exercise patterns.
Inputs: start_date, end_date.
get_cardiovascular_ageC
Get your estimated cardiovascular (vascular) age based on heart health metrics. Compare your vascular age to your actual age to understand your cardiovascular health.
Inputs: start_date, end_date.
get_daily_sleepA
Get daily sleep scores and contributors (efficiency, deep sleep, REM sleep, latency, timing, etc.). Different from get_sleep - this provides a single daily score with breakdown of what contributed to it. Use this for understanding sleep quality scoring.
Inputs: start_date, end_date.
get_enhanced_tagsA
Get enhanced tags with rich data including custom tags, timestamps, and durations. Enhanced tags include predefined categories (sleep_aid, caffeine, alcohol, etc.) and custom user-created tags with names like medications, supplements, or lifestyle factors.
Inputs: start_date, end_date.
get_heart_rateA
Get individual heart rate readings throughout the day with timestamps and source (awake, rest, sleep, workout, etc.). Returns detailed time-series data. Use this for analyzing heart rate patterns, variability throughout the day, or correlating HR with activities.
Inputs: start_date, end_date.
get_personal_infoA
Get your Oura profile information including age, weight, height, and biological sex. This data is used by Oura to personalize insights.
Inputs: no named parameters.
get_readinessA
Get daily readiness scores and contributors (HRV balance, resting heart rate, body temperature, recovery). Use this to understand recovery and readiness to perform.
Inputs: start_date, end_date.
get_resilienceA
Get daily resilience scores showing your body's capacity to recover from stress. Includes sleep recovery, daytime recovery, and stress contributors. Resilience levels range from limited to exceptional.
Inputs: start_date, end_date.
get_rest_modeA
Get rest mode periods when you've enabled rest mode in the Oura app (typically during illness or recovery). Shows when rest mode was active and any notes.
Inputs: start_date, end_date.
get_ring_infoA
Get information about your Oura ring hardware including model, color, firmware version, and configuration.
Inputs: no named parameters.
get_sessionsA
Get meditation, breathing, and relaxation sessions recorded with Oura. Includes session type, duration, and biometrics like heart rate and HRV during the session.
Inputs: start_date, end_date.
get_sleepA
Get detailed sleep data for a date range. Returns sleep duration, stages (deep/REM/light), efficiency, heart rate, and HRV. Use this for analyzing sleep patterns and quality.
Inputs: start_date, end_date.
get_sleep_timeA
Get Oura's personalized bedtime recommendations. Shows your ideal bedtime window based on your sleep patterns and circadian rhythm.
Inputs: start_date, end_date.
get_spo2B
Get daily SpO2 (blood oxygen saturation) percentage and breathing disturbance index. Use this to monitor respiratory health, detect sleep apnea patterns, or understand overnight oxygen levels.
Inputs: start_date, end_date.
get_stressA
Get daily stress levels and recovery time. Shows time spent in high stress vs high recovery zones, plus overall day summary (restored/normal/stressful). Use this to understand stress patterns and recovery balance.
Inputs: start_date, end_date.
get_tagsB
Get user-created tags and notes. Tags help track lifestyle factors like caffeine, alcohol, meals, or custom notes that may affect sleep and recovery.
Inputs: start_date, end_date.
get_vo2_maxA
Get VO2 max measurements (cardiorespiratory fitness). VO2 max indicates the maximum amount of oxygen your body can use during intense exercise. Higher values indicate better cardiovascular fitness. Use this to track fitness improvements over time.
Inputs: start_date, end_date.
get_workoutsB
Get workout sessions with activity type, duration, intensity, calories burned, and distance. Use this to analyze exercise patterns, workout frequency, and training load.
Inputs: start_date, end_date.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 27 tools
Most tools have distinct purposes, with clear separation between retrieval (get_*) and analysis (analyze_*, compare_*, etc.). However, there is some potential overlap among analytical tools like analyze_sleep_quality, best_sleep_conditions, and compare_conditions, which could cause confusion for an agent without careful reading of descriptions.
The naming uses multiple verb styles (get, analyze, compare, correlate, detect) and one adjective phrase (best_sleep_conditions), making the pattern inconsistent. While each verb indicates a function, the lack of a single predictable convention reduces coherence.
With 27 tools, the server is on the high side for a single-domain MCP. While each tool seems justified by the rich Oura data model, the quantity may overwhelm agents and suggests potential over-scoping.
The tool set covers a wide range of Oura metrics (sleep, activity, HRV, temperature, tags, workouts, etc.) and provides both data retrieval and analysis. Minor gaps exist, such as no create/update operations for tags or sessions, but these are reasonable for a read-and-analyze focused server.
Maintenance
Related MCP Connectors
WHOOP recovery, strain, sleep and workouts in Claude via official WHOOP OAuth. Free, open source.
Connect your Oura Ring account securely in minutes. Enable authorized access to your sleep, activi…
Connect your wearables, rings and training apps, then ask your AI about your own health data.
Connect your Oura Ring account and enable access to your wellness data in apps and automations. In…
Related MCP Servers
- 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.ISC
- FlicenseNot gradedqualityDmaintenanceIntegrates Oura Ring health data with Claude Desktop, providing resources, tools, and advanced analytics for sleep, activity, readiness, and health trends.1-
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to access your Oura Ring health data through OAuth2-authenticated API calls.9MIT
- AlicenseAqualityBmaintenanceAsk your Oura Ring about sleep, readiness, activity, stress and heart rate in ChatGPT or Claude, in any language. Read-only, 10 task-oriented tools; runs in a sandbox demo mode with no credentials.1027 npm1MIT