Privacy-first, unofficial Oura MCP server for AI health, sleep, activity and heart-rate agents.
Privacy-first, unofficial Oura MCP server for AI health, sleep, activity and heart-rate agents.
Give your AI agent your Oura readiness, sleep, activity and HRV — without copy-pasting from the Oura app.
http://127.0.0.1:3000/callbackCompare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| oura_demo | realistic synthetic readiness/sleep/activity payloads (no account needed; see [Quickstart](#quickstart-see-the-data-before-you-connect)) |
| oura_quickstart | personalized 3-step setup walkthrough that adapts to your current state |
| oura_connection_status | verify local setup before calling Oura |
| oura_data_inventory | inventory supported data domains, scopes, privacy modes and recommended first calls without calling Oura APIs. |
| oura_daily_summary | readiness, sleep, activity and SpO2 brief for today |
| oura_weekly_summary | scorecard, comparison vs prior week, next-week plan |
{
"mcpServers": {
"oura": {
"command": "npx",
"args": ["-y", "oura-mcp-unofficial"]
}
}
}Configuration as documented by the project. Restart the client after saving.
http://127.0.0.1:3000/callback| Variable | Description | Required |
|---|---|---|
| OURA_CLIENT_ID | Configuration value read at startup. | Optional |
| OURA_CLIENT_SECRET | Credential the server authenticates with. | Yes |
| OURA_TOKEN_PATH | Credential the server authenticates with. | Yes |
| OURA_CACHE_PATH | Filesystem location the server is allowed to use. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Generate your daily standup from real GitHub, Jira, Linear, and Slack activity.
An implementation of Giphy integration with Model Context Protocol
Ingest and search LogsLoom logs from coding agents.
Local MCP bridge: your coding agent designs on Brilliant's real vector canvas, fully on 127.0.0.1.