What is mcp-server AGENTS.md?

Repository instructions for developing the Iris MCP server, a TypeScript program that evaluates AI agent output for quality, safety, and cost.

Use them when changing the server, its evaluation engine, storage, dashboard, command-line tools, or related packages, especially before running the fast preflight and tests.

They give coding agents the project's layout, supported runtime, build expectations, and required checks so changes follow the repository's rules.

How iris-eval/mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to iris-eval/mcp-server. 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/iris-eval/mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/iris-eval/mcp-server

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/iris-eval/mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/iris-eval/mcp-server/agents-md)

Your own site

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

Per session 2,054 This file is loaded in full into every session.

When invoked 2,054 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	$0.02054	$0.02054
Opus 5.5	$0.00822	$0.00822
Sonnet 5.5	$0.00411	$0.00411
Haiku 4.5	$0.00205	$0.00205

Measured 3d ago against content hash c4b5bed95271, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-server 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 3d 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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

How to build, test and land a change in this repository. Written for coding agents; it holds for people too. CONTRIBUTING.md is the longer version of the same rules, and wins if the two ever disagree.

Iris is an MCP server that evaluates AI agent output for quality, safety and cost. TypeScript, ESM only, Node.js 22.13 or later. The server is src/, built to dist/, and published to npm as @iris-eval/mcp-server. How the pieces fit: docs/architecture.md.

Layout

Path	What it is
`src/tools/`	The MCP tools, one file each
`src/eval/`	The evaluation engine and the verdict; built-in rules in `src/eval/rules/`, the optional model judge in `src/eval/llm-judge/`
`src/storage/`	SQLite storage (better-sqlite3, or Node's built-in `node:sqlite`)
`src/dashboard/`	The dashboard's HTTP server: its API and the `POST /api/v1/traces` ingest
`src/cli/`	`install`, `ingest` and `export`
`dashboard/`	The web dashboard: Vite and React, its own `package.json` and lockfile, built into `dist/dashboard`
`website/`	iris-eval.com: Next.js, its own `package.json` and lockfile
`packages/`	`sdk` (`@iris-eval/sdk`), `langchain` (`@iris-eval/langchain`), `python` (`iris-eval` on PyPI) and `iris-eval` (the npm launcher). Each versions on its own
`tests/`	Vitest: `unit/`, `integration/`, `proof/`; Playwright in `e2e/`; contract tests at the top level that hold the docs, manifests and site to the code
`proof/`	The labelled corpus and the runner behind the published accuracy of every rule
`scripts/`	Build, release and preflight scripts; `scripts/claims/` generates and checks the truthbase
`.claims.json`	The truthbase: every public number (rules, patterns, tools, version), generated from source
`clients.json`	One row per MCP client Iris names, with how it is checked

Setup

npm ci
npm --prefix dashboard ci
npm --prefix website ci
git config core.hooksPath scripts/git-hooks   # the pre-push hook: refuses a tree the preflight has not passed

Read the full file on GitHub · 107 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.

3d ago First seen · 107 lines · 2,054 tokens per session scan A c4b5bed95271

Subscribe to this mod's changes

mcp-server AGENTS.md is an instructions file published in the GitHub repository iris-eval/mcp-server (9 stars, last pushed 3d ago), licensed MIT. It adds 2,054 tokens to every session, about $0.0082 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 2026-11-04.

Building agents LLM Testing agent-evaluation ai-agent claude eval mcp

mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-server AGENTS.mdiris-eval/mcp-server	Instructions file	9	3d ago	MIT	A	2,054	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

mcp-server: Instructions file for Codex