Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add davidmosiah/oura-mcp --skill oura-mcpgit clone --depth 1 https://github.com/davidmosiah/oura-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/davidmosiah/oura-mcp/oura-mcp)<a href="https://agentmods.dev/skills/davidmosiah/oura-mcp/oura-mcp"><img src="https://agentmods.dev/badge/skills/davidmosiah/oura-mcp/oura-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/davidmosiah/oura-mcp/oura-mcp"><img src="https://agentmods.dev/badge/skills/davidmosiah/oura-mcp/oura-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.00543 |
| Opus 5.5 | $0.00032 | $0.00217 |
| Sonnet 5.5 | $0.00016 | $0.00109 |
| Haiku 4.5 | $0.00008 | $0.00054 |
Grade A, and why
oura-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Oura
MCP server oura from the [email protected] npm package, run locally through npx. It reads readiness, sleep stages and score, HRV, resting heart rate, activity, workouts and tags. Data source: the official Oura Cloud API v2.
Workflow
- Start with
oura_connection_status. Then pick what fits the question:oura_daily_summary,oura_weekly_summary. - If
oura_connection_statusreports the connector is not ready, calloura_demofor clearly labelled synthetic data so the user sees the shape of the answer, then give them the setup commands below to run in their own terminal. - Lead with the answer to the user's question, then the two or three numbers that support it, with dates. Say when data is missing or stale instead of filling gaps.
Setup (the user runs this in a terminal, not in chat)
npx -y [email protected] setup --client generic
npx -y [email protected] auth
npx -y [email protected] doctor
setup asks for the Oura developer app client ID and secret and saves them locally (--client generic because this plugin already registers the server with Hermes); auth opens the Oura consent page in the browser and stores the OAuth tokens under ~/.oura-mcp/ with 0600 permissions; doctor confirms readiness.
Safety
- Never ask the user to paste client secrets, passwords, tokens or MFA codes into the chat; setup happens in their terminal.
- Tools that change local state: oura_profile_update (local profile only), oura_exchange_code (stores OAuth tokens locally). Use them only when the user asks.
- Destructive: oura_revoke_access (revokes the Oura grant and deletes local tokens). Confirm with the user first.
- Not medical advice: the data supports personal reflection and planning, not diagnosis or treatment. Point the user to a clinician for symptoms, medication or anything urgent.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 33 lines · 79 tokens per session scan A 567b36da931d
oura-mcp is a skill published in the GitHub repository davidmosiah/oura-mcp (5 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 543 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.
oura-mcp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| oura-mcpdavidmosiah/oura-mcp | Skill | 5 | yesterday | MIT | A | 79 | Claude Code, Codex |
| withings-mcpdavidmosiah/withings-mcp | Skill | 5 | yesterday | MIT | A | 76 | Claude Code, Codex |
| withingsdavidmosiah/withings-mcp | Skill | 5 | yesterday | MIT | A | 38 | Claude Code, Codex |
| garmin-connectbpauli/gccli | Skill | 31 | 2d ago | MIT | A | 27 | Claude Code, Codex |
| verifymeltforce/FreeReps | Skill | 23 | yesterday | MIT | A | 97 | Claude Code, Codex |
| icuvisor-trainingricardocabral/icuvisor | Skill | 41 | yesterday | MIT | A | 48 | Claude Code, Codex |
| garmin-trainerbpauli/gccli | Skill | 31 | 2d ago | MIT | A | 85 | Claude Code, Codex |