korea-stats-mcp: Instructions file for Codex

AGENTS.md

korea-stats-mcp AGENTS.md is an instructions file for Codex, OpenCode from Dayoooun/korea-stats-mcp. It costs 929 tokens per session, scanned A, original, MIT.

Project instructions for a server that lets AI coding tools query South Korea’s official KOSIS statistics through natural-language requests. It documents the code layout, commands, tests, and deployment details.

In plain words
What is it for?
It helps developers install, run, test, build, lint, and deploy the KOSIS statistics server.
Why use it?
It gives contributors the repository-specific context they need instead of making them infer how the MCP server works. MCP is a standard way for an AI tool to call outside data or actions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Claude Code; mentions Codex.

This is Dayoooun/korea-stats-mcp's own configuration. It tells Codex and OpenCode how to work on korea-stats-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 korea-stats-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dayoooun/korea-stats-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dayoooun/korea-stats-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 929 This file is loaded in full into every session.
When invoked 929 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 $0.00929 $0.00929
Opus 5.5 $0.00372 $0.00372
Sonnet 5.5 $0.00186 $0.00186
Haiku 4.5 $0.00093 $0.00093

Measured today against content hash cf3af805d8dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

korea-stats-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 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.

AGENTS.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

korea-stats-mcp — KOSIS 국가통계를 자연어로 조회하는 MCP 서버

왜 있나

  • 누구를 위한 무엇인가: Claude Code·Codex 등 MCP 클라이언트가 통계청 KOSIS OpenAPI로 최신 공식 통계를 조회하게 한다. 원격(Vercel)과 로컬(npm/stdio) 두 경로로 제공한다.
  • 지금 상태: 운영 중. package.json 버전 2.0.0, npm 패키지 @kimdayoun/korea-stats-mcp, 원격 https://korea-stats-mcp.vercel.app/mcp.

구조

src/        MCP 서버 본체 (index.ts·server.ts·remoteProxy.ts, tools/ api/ cache/ data/ prompts/ resources/ utils/)
api/mcp.ts  Vercel 서버리스 진입점 (vercel.json 이 /mcp, / 를 여기로 보낸다)
tests/      node --test 단위(*.test.mjs) + Playwright 스펙(*.spec.ts, release-*)
docs/       USER_GUIDE.md (운영자 절차 포함), USABILITY_IMPROVEMENT.md
dist/       tsc 빌드 산출물 (bin 진입점)

명령

할 일 명령
설치 pnpm install --frozen-lockfile (vercel.json installCommand 기준. 로컬 설치 명령은 미확인)
개발 실행 npm run dev (tsc --watch), npm run start (node dist/index.js)
테스트 npm run test:core (빌드 후 node --test), npm run test:offline, npm run test:live, npm test (playwright)
빌드·린트 npm run build, npm run lint
배포 npm: prepublishOnly 가 빌드. Vercel: 명령 미확인 (vercel.json 존재, CI 워크플로 없음)

배포와 확인

  • 어디에 도나: Vercel korea-stats-mcp.vercel.app (함수 리전 icn1, 최대 15초), npm @kimdayoun/korea-stats-mcp.
  • 자동/수동: 미확인. .github/ 없음.
  • 배포 확인: 실제 배포본의 tools/list 로 확인한다(README 지침). 로컬 성공이나 npm 게시를 운영 배포 완료로 보지 않는다. 절차는 docs/USER_GUIDE.md 운영자 절차.

이 저장소에서 승인이 필요한 일

  • Vercel 운영 배포: 공개 원격 서버가 바뀐다. 환경 변수 KOSIS_API_KEY, DATA_GO_KR_SERVICE_KEY 설정 변경 포함.
  • npm 게시: 공개 패키지 버전은 되돌리기 어렵다.
  • 과거 공개 키 폐기: 새 키 정상 동작을 확인한 뒤에만 한다(README).

하지 않는 것

  • API 키를 프런트엔드 공개 환경변수·저장소·로그에 넣지 않는다: README가 명시한다. .env.example 만 두고 .env 값은 출력하지 않는다.
  • 스코프 없는 kosis-mcp 등을 이 프로젝트 배포본으로 취급하지 않는다: 제3자 패키지다(README).
  • 소스 개선이 npm·운영 배포본에 이미 반영됐다고 가정하지 않는다: 소스·npm·Vercel 버전이 별개다(README).
  • test-results.json 등 테스트 산출물의 수정분을 임의로 되돌리거나 커밋하지 않는다: 현재 test-results.json 이 수정 상태(미커밋)다.

사고 이력

  • 과거 공개 KOSIS 키가 소스·Git 이력에 노출됐던 정황이 있다(README: 소스 삭제로 이력에서 사라지지 않음) → 새 키로 검증 후 폐기한다.
  • 최근 커밋 fix(tools): make itemId optional for item-less KOSIS tables → 항목 없는 KOSIS 통계표가 있으므로 itemId 를 필수로 가정하지 않는다.

Read the full file on GitHub · 51 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. today First seen · 51 lines · 929 tokens per session scan A cf3af805d8dd

Subscribe to this mod's changes

korea-stats-mcp AGENTS.md is an instructions file published in the GitHub repository Dayoooun/korea-stats-mcp (17 stars, last pushed yesterday), licensed MIT. It adds 929 tokens to every session, about $0.0037 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.

Related

korea-stats-mcp AGENTS.md compared with instructions from other repositories

korea-stats-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
korea-stats-mcp AGENTS.mdDayoooun/korea-stats-mcpInstructions file17yesterdayMITA929Codex, 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