metmuseum-mcp: Instructions file for Codex

AGENTS.md

metmuseum-mcp AGENTS.md is an instructions file for Codex, OpenCode from mikechao/metmuseum-mcp. It costs 576 tokens per session, scanned A, original, MIT.

A set of repository instructions for a TypeScript MCP server that connects coding agents to The Met museum's public collection API.

In plain words
What is it for?
Use it when building, linting, type-checking, testing, or modifying the server and its museum-search tools.
Why use it?
It gives an agent the project's file layout, commands, coding rules, and testing expectations so changes follow the repository's conventions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is mikechao/metmuseum-mcp's own configuration. It tells Codex and OpenCode how to work on metmuseum-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metmuseum-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mikechao/metmuseum-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/mikechao/metmuseum-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mikechao/metmuseum-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.

agentmods badge for metmuseum-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mikechao/metmuseum-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/mikechao/metmuseum-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mikechao/metmuseum-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mikechao/metmuseum-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.

agentmods 80×15 button for metmuseum-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mikechao/metmuseum-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mikechao/metmuseum-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 576 This file is loaded in full into every session.
When invoked 576 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00576 $0.00576
Opus 5.5 $0.00230 $0.00230
Sonnet 5.5 $0.00115 $0.00115
Haiku 4.5 $0.00058 $0.00058

Measured 2mo ago against content hash 1886b032c663, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

metmuseum-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 2mo 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 · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

The codebase is a TypeScript MCP server for The Met API.

  • src/index.ts: entrypoint (stdio by default, --http for Streamable HTTP).
  • src/MetMuseumServer.ts: server composition and registration.
  • src/tools/: MCP tools (ListDepartmentsTool.ts, SearchMuseumObjectsTool.ts, GetObjectTool.ts).
  • src/handlers/: request/response handlers.
  • src/utils/ and src/types/: shared utilities and type definitions.
  • dist/: build output generated by pnpm run build (do not hand-edit).
  • .github/workflows/publish.yml: release workflow for npm publish + MCPB packaging.

Build, Test, and Development Commands

  • pnpm install: install dependencies (use CI=true pnpm install --frozen-lockfile in CI).
  • pnpm run build: compile TypeScript to dist/ and set executable bits.
  • pnpm run lint: run ESLint with auto-fix.
  • pnpm run lint:check: lint without file changes.
  • pnpm run typecheck: strict TS compile checks without emitting files.
  • pnpm run check: full local gate (lint:check + typecheck).
  • node dist/index.js --http: smoke-test HTTP transport on http://localhost:3001/mcp.

Coding Style & Naming Conventions

Use the existing ESLint config (@antfu/eslint-config) and keep formatting consistent:

  • 2-space indentation, semicolons, single quotes.
  • ESM/TypeScript modules ("type": "module").
  • Keep tool/handler classes in PascalCase.ts; utility modules may use kebab-case.ts (for example, server-utils.ts).
  • Prefer small, focused modules; place shared types in src/types/types.ts.

Testing Guidelines

There is currently no dedicated unit-test framework in this repository. For contributions:

  • Run pnpm run check before opening a PR.
  • Smoke-test the built server (pnpm run build then node dist/index.js --http).
  • If adding tests, use *.test.ts naming and place them close to the feature or under a src/__tests__/ folder.

Commit & Pull Request Guidelines

Read the full file on GitHub · 50 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.

  1. 2mo ago First seen · 50 lines · 576 tokens per session scan A 1886b032c663

Subscribe to this mod's changes

metmuseum-mcp AGENTS.md is an instructions file published in the GitHub repository mikechao/metmuseum-mcp (35 stars, last pushed 6mo ago), licensed MIT. It adds 576 tokens to every session, about $0.0023 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 2026-08-30.

Related

metmuseum-mcp AGENTS.md compared with instructions from other repositories

metmuseum-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
metmuseum-mcp AGENTS.mdmikechao/metmuseum-mcpInstructions file356mo agoMITA576Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode