# oura-ring-mcp [Health: Active]

**Category:** 🧬 Biology & Bioinformatics  
**Repository:** https://github.com/mitchhankins01/oura-ring-mcp  
**GitHub Stars:** 32  
**npm Downloads (last month):** 339  
**Views:** 8  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/oura-ring-mcp

## Description
Connect your Oura Ring to Claude AI assistants. Health metrics with smart analysis tools.

## Tools
Capabilities this server exposes over MCP:

- **get_sleep** — Sleep data with stages, efficiency, HR, HRV
- **get_daily_sleep** — Daily sleep scores with contributors
- **get_readiness** — Readiness scores and recovery metrics
- **get_activity** — Steps, calories, intensity breakdown
- **get_workouts** — Workout sessions with type and intensity
- **get_sessions** — Meditation and relaxation sessions
- **get_heart_rate** — HR readings throughout the day
- **get_stress** — Stress levels and recovery time
- **get_spo2** — Blood oxygen and breathing disturbance
- **get_tags** — User-created tags and notes
- **detect_anomalies** — Find unusual readings using outlier detection
- **analyze_sleep_quality** — Sleep analysis with trends, patterns, debt
- **correlate_metrics** — Find correlations between health metrics
- **compare_periods** — Compare this week vs last week
- **compare_conditions** — Compare metrics with/without a tag
- **best_sleep_conditions** — What predicts your good vs poor sleep
- **analyze_hrv_trend** — HRV trend with rolling averages

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "oura-ring-mcp": {
    "command": "npx",
    "args": ["-y","oura-ring-mcp"],
    "env": {
      "OURA_ACCESS_TOKEN": "",
      "OURA_CLIENT_ID": "",
      "OURA_CLIENT_SECRET": "",
      "NODE_ENV": "",
      "MCP_SECRET": ""
    }
  }
}
```

**Requires environment variables:** `OURA_ACCESS_TOKEN`, `OURA_CLIENT_ID`, `OURA_CLIENT_SECRET`, `NODE_ENV`, `MCP_SECRET` — the values above are empty placeholders; fill in real credentials before running (see the repository for what each one is for).

## Documentation

## What oura-ring-mcp MCP server does

The oura-ring-mcp MCP server exposes Oura Ring health data and analysis functions through the Model Context Protocol. It is designed for assistants that need to answer questions about sleep, recovery, activity, and related personal metrics using data from an Oura account.

Data retrieval covers sleep stages, sleep efficiency, heart rate, HRV, daily sleep scores, readiness contributors, steps, calories, activity intensity, workouts, meditation and relaxation sessions, stress, blood oxygen, breathing disturbance, and user-created tags or notes. Returned information is formatted for human reading, including durations and contextual score labels.

The server also includes analysis functions. These can identify unusual readings, examine sleep quality and debt, calculate relationships between metrics, compare time periods, compare tagged and untagged conditions, identify conditions associated with better sleep, and calculate rolling HRV trends.

## How it works

The server can authenticate with an Oura Personal Access Token or through an OAuth flow. With OAuth, credentials are stored locally in `~/.oura-mcp/credentials.json`; client credentials can also be supplied to support automatic token refresh. The local configuration uses the MCP server command as a stdio process.

In addition to tools, the server publishes Oura-oriented resources for today’s summary, a seven-day summary, 30-day baselines, monthly insights, and tag usage. It also provides prompts for weekly reviews, sleep optimization, recovery checks, week comparisons, and tag analysis.

For remote use, the project documents deployment on Railway. The HTTP deployment can proxy OAuth through Oura, or it can accept a static bearer token for MCP access together with an Oura Personal Access Token. Claude.ai can connect through its MCP connector, while Claude Desktop can connect to the remote `/mcp` endpoint with an authorization header.

## Setup and configuration

Install the package globally with npm or run it directly through `npx`. Node.js 18 or newer is required. For token authentication, create an Oura Personal Access Token and provide it as `OURA_ACCESS_TOKEN` in the MCP client configuration.

For OAuth, create an application with Oura, use `http://localhost:3000/callback` as the local redirect URI, and run the authentication command with `OURA_CLIENT_ID` and `OURA_CLIENT_SECRET`. The resulting credentials are saved under the user’s home directory. Add the client ID and secret to the MCP configuration if automatic refresh is needed.

Remote Railway deployments use `OURA_CLIENT_ID`, `OURA_CLIENT_SECRET`, and `NODE_ENV=production`. `MCP_SECRET` can protect MCP requests with a static bearer token. `OURA_ACCESS_TOKEN` is available as a fallback for remote deployments, but the documented fallback also requires `MCP_SECRET`.

## Tools and capabilities

The oura-ring-mcp MCP server provides these tool groups:

- Retrieval: `get_sleep`, `get_daily_sleep`, `get_readiness`, `get_activity`, `get_workouts`, `get_sessions`, `get_heart_rate`, `get_stress`, `get_spo2`, and `get_tags`.
- Analysis: `detect_anomalies`, `analyze_sleep_quality`, `correlate_metrics`, `compare_periods`, `compare_conditions`, `best_sleep_conditions`, and `analyze_hrv_trend`.

These tools support questions such as whether sleep changed between weeks, whether a tag is associated with different metrics, whether HRV is rising or falling, and which conditions correspond with better sleep.

## Limitations and notes

The server depends on access to an Oura account and its available data. Analysis results are based on the metrics and tags returned by Oura; the documentation does not describe them as medical diagnoses. Remote deployments require separate Oura OAuth configuration or the documented token and bearer-secret setup. The README provides explicit Claude Desktop and Claude.ai connection instructions; other client configurations are not documented there.

The project is licensed under MIT.

_Full upstream README: https://allmcps.com/mcp/oura-ring-mcp/readme_