What is oura-mcp AGENTS.md?

A repository handoff document for an MCP server that connects to the Oura v2 API, which provides health and fitness data. It explains the project’s purpose, known API failures, fixes, publishing process, and current blockers.

Use it when maintaining, debugging, or publishing the Oura MCP server. It is especially relevant to pagination, date handling, latest-value queries, and release work.

It gives the next coding agent the project’s current state and prevents it from repeating outdated assumptions about pagination and API behavior.

How proscar87/oura-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to proscar87/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.

Copy the file

curl -O https://raw.githubusercontent.com/proscar87/oura-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/proscar87/oura-mcp

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/proscar87/oura-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/proscar87/oura-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/proscar87/oura-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/proscar87/oura-mcp/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/proscar87/oura-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/proscar87/oura-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,081 This file is loaded in full into every session.

When invoked 4,081 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.04081	$0.04081
Opus 5.5	$0.01632	$0.01632
Sonnet 5.5	$0.00816	$0.00816
Haiku 4.5	$0.00408	$0.00408

Measured 23d ago against content hash 94794fce5c02, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

oura-mcp AGENTS.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 23d 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.

AGENTS.md · 319 lines

How it starts

The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.

For the next agent

State as of 10 August 2026, after a twelve-round audit. Read this before touching anything.

What this is

An MCP server over the Oura v2 API. Its reason to exist is that Oura under-delivers without saying so, and that's corrected here.

Be careful how you tell that story, because it changed. An earlier version of this file said the differentiator was pagination, and that "of the seven Oura MCP servers, the most complete one doesn't paginate." That is no longer true: benngermin/oura-mcp paginates properly, with a resumable cursor. Pagination is table stakes now, not the edge. Don't repeat that line.

What does hold the project up are four silent failures of the same family, measured against the real API and corrected here:

	The failure	Where the fix lives
1	Not following `next_token` returns a fraction. One local day of `heartrate` is 1,231 samples across 2 pages	the pagination loop in the client
2	`end_date` is inconsistent across collections, and `workout` filters by UTC date while reporting `day` in local time	`EXTRA_DAYS` and the trim step
3	`latest=true` where it doesn't apply → Oura returns the whole collection	`WITH_LATEST`, rejected before the network
4	`fields=made_up` → returns the complete record, no projection	the ignored-fields check

If anyone proposes "simplifying" any of those four, the answer is no. They are the product.

Where it's published


GitHub	https://github.com/proscar87/oura-mcp — public, MIT, CI green
PyPI	https://pypi.org/project/mcp-oura/ — 0.1.0, 0.1.1, 0.2.0
MCP registry	`io.github.proscar87/oura-mcp` v0.2.0, active, latest

The install name is mcp-oura because oura-mcp was already taken on PyPI by a 0.1.0 package with no author and no repository. The imported module is still oura_mcp.

How to publish a new version

# bump the number in pyproject.toml AND server.json — they must match
git tag v0.2.1 && git push origin v0.2.1

Read the full file on GitHub · 319 lines

Changes

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.

23d ago Changed · +4 lines · +53 tokens per session 94794fce5c02
26d ago Changed · +3 lines · +44 tokens per session 55ba490a1017
1mo ago Changed · +8 lines · +103 tokens per session 52c3a423cefa
1mo ago Changed · +36 lines · +510 tokens per session 6eeba287b8b6
1mo ago Changed a9e9bd295ee6
2mo ago Changed · +10 lines · +185 tokens per session 20ef4ed0a039
2mo ago First seen · 258 lines · 3,186 tokens per session scan A a2a191d366d1

Subscribe to this mod's changes

oura-mcp AGENTS.md is an instructions file published in the GitHub repository proscar87/oura-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 4,081 tokens to every session, about $0.0163 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 2026-08-31.

oura-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
oura-mcp AGENTS.mdproscar87/oura-mcp	Instructions file	0	10d ago	MIT	A	4,081	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

oura-mcp: Instructions file for Codex