Oura MCP. Analyze sleep cycles, readiness, and recovery metrics.

Your AI agent connects straight to your Oura Ring health data stream. You don't have to jump between apps or pore over dashboards; you just ask a question in plain language, and the server gives you the numbers. It lets you analyze complex patterns—like how poor sleep impacts your recovery score—using nothing but conversation.

Analyze Sleep Cycles: When you need to know about sleep efficiency, use get_sleep. This tool pulls detailed data covering your time spent in REM sleep, deep sleep, light sleep, and periods when you were awake. You can check these stages over any specific date range to see patterns in your nightly rest.

Assess Recovery Status: To quickly gauge how recovered you are, run get_readiness. This gives you your daily readiness score alongside crucial metrics like your resting heart rate, body temperature, and overall recovery status for a given period. It's your quick check on whether you can push it or if you need to chill out.

Track Physical Activity Trends: For general fitness tracking, get_activity retrieves your daily performance data. You get the step count, total calories burned, and MET minutes across any date range you specify. This helps you see how your physical output changes week over week.

Review Exercise Performance: Want to look back at a specific workout? The get_workouts tool gathers a complete list of every logged session. For each one, it provides the type of exercise, how long it lasted, and the estimated calories burned. It’s a straightforward log of your physical effort.

Get High-Frequency Heart Data: When you need deep metrics, use get_heart_rate. This feature pulls detailed heart rate samples and corresponding HRV data points for every five minutes within a narrow date window. You gotta remember to keep those dates tight here; this is high-resolution stuff.

Correlate Behaviors with Health Metrics: Sometimes the data isn't enough—you need context. get_tags lets your agent read your manual entries, like notes on how you felt or your energy levels. You can then cross-reference those subjective feelings against hard metrics like sleep scores or readiness readings to find connections.

View Summaries and Overviews: Need a big-picture view for a whole period? get_sessions gives you an overall summary that bundles together the key sleep scores, activity totals, and major readiness indicators for the entire span of time you're interested in. It’s a solid starting point before diving into granular details.

Putting it Together: You can track your full health picture by querying these tools together. For example, you'll get get_sleep data to check your REM and deep cycles; then you'll run get_readiness on the same dates to see if poor sleep correlated with a lower recovery score. If you want more depth, you can cross-reference that using get_tags, noting whether you felt stressed or energized during those low-scoring days.

It all comes down to asking specific questions: 'What was my average deep sleep duration last month?' (using get_sleep) or 'How did my readiness score change in the week I started running more often?' (combining get_readiness and get_activity). Your agent handles the data retrieval from all these sources—from basic step counts via get_activity to complex HRV readings via get_heart_rate—so you just get the answer.

It's built for deep analysis, letting you stop staring at dashboards and start talking about your health.