Borrowing it
Nothing to install: this file belongs to Rajskij/oura-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Rajskij/oura-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Rajskij/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/instructions/rajskij/oura-mcp/claude-md)<a href="https://agentmods.dev/instructions/rajskij/oura-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rajskij/oura-mcp/claude-md/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/instructions/rajskij/oura-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rajskij/oura-mcp/claude-md.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 | $0.00710 | $0.00710 |
| Opus 5 | $0.00355 | $0.00355 |
| Sonnet 5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
oura-mcp CLAUDE.md 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 10d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Remote MCP server that exposes Oura Ring data (sleep, readiness, activity, stress, heart rate) to MCP clients like ChatGPT and Claude. The client model does all interpretation and translation; this server only returns compact, well-shaped data.
If CLAUDE.local.md or docs/ROADMAP.md exist in your checkout (both are gitignored), read them first. They hold the current plan and private context. docs/ARCHITECTURE.md (public) is the code map: where things live and which invariants to keep.
Current phase: 2 — showcase (self-host distribution)
The server itself stays single-user: one Oura account, no auth between the MCP client and this server (a long random URL path instead), deployed on an Oracle free-tier VM (x86_64). Phase 2 is polish and distribution of that same server: README and architecture docs, releases, MCP catalog listings, a Claude Desktop .mcpb bundle, a Cloudflare Workers entry.
Never build, regardless of phase — barred by Oura's API terms, not deferred: multi-tenant hosting, an OAuth server between MCP clients and this server, databases holding other people's tokens, anything that routes third-party user data through infrastructure we run. docs/ARCHITECTURE.md ("Self-host distribution") has the short version of why.
Stack
- Node.js 22+, TypeScript strict, no
any - MCP: official
@modelcontextprotocol/sdk, Streamable HTTP transport (not SSE, which is deprecated in the MCP spec) — wired through@hono/mcp(StreamableHTTPTransport), which speaks Hono'sContextdirectly instead of bridging Node req/res - HTTP framework: Hono
- Phase 1 token storage:
data/tokens.json(gitignored) - Deploy target: Oracle Cloud free-tier VM (x86_64, Ubuntu 24.04, 1 GB RAM + 2 GB swap), Caddy for TLS, systemd
- Keep all Oura API code in
src/providers/oura.ts. That module boundary is the only concession to a possible multi-provider future.
Commands
npm run dev— run locally with watch (tsx)npm run typecheck— TypeScript check, run after every changenpm run get-token— one-time local OAuth flow, saves tokens todata/tokens.jsonnpm run build/npm start— production build and run
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.
- 10d ago First seen · 37 lines · 710 tokens per session scan A 25432bc0df97
oura-mcp CLAUDE.md is an instructions file published in the GitHub repository Rajskij/oura-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 710 tokens to every session, about $0.0036 per session on Opus 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 2026-08-31.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.