Borrowing it
Nothing to install: this file belongs to Koomook/data-go-mcp-servers. 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/Koomook/data-go-mcp-servers/main/CLAUDE.mdgit clone --depth 1 https://github.com/Koomook/data-go-mcp-serversWrote 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/koomook/data-go-mcp-servers/claude-md)<a href="https://agentmods.dev/instructions/koomook/data-go-mcp-servers/claude-md"><img src="https://agentmods.dev/badge/instructions/koomook/data-go-mcp-servers/claude-md.svg" alt="Measured on agentmods" 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 | $0.01926 | $0.01926 |
| Opus 5 | $0.00963 | $0.00963 |
| Sonnet 5 | $0.00385 | $0.00385 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
data-go-mcp-servers 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 6d 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Korea Data.go.kr MCP Servers - Development Guide
이 프로젝트는 한국 공공 데이터 포털(data.go.kr)의 API를 Model Context Protocol (MCP) 서버로 제공합니다.
프로젝트 구조
data-go-mcp-servers/
├── src/ # MCP 서버들
│ ├── nps-business-enrollment/ # 국민연금공단 사업장 가입 내역
│ ├── nts-business-verification/ # 국세청 사업자등록정보
│ ├── fsc-financial-info/ # 금융감독원 금융회사 정보
│ ├── presidential-speeches/ # 대통령기록관 연설기록
│ ├── pps-narajangteo/ # 조달청 나라장터 정보
│ └── msds-chemical-info/ # 화학물질안전원 MSDS 정보
│ ├── pyproject.toml # 패키지 설정 (PyPI 배포용)
│ ├── data_go_mcp/
│ │ └── {module_name}/
│ │ ├── server.py # MCP 서버 구현
│ │ ├── api_client.py # API 클라이언트
│ │ └── models.py # 데이터 모델
│ └── tests/ # 테스트 코드
├── template/ # Cookiecutter 템플릿
├── scripts/
│ └── deploy_to_pypi.py # PyPI 배포 자동화 스크립트
├── CONTRIBUTING.md # 새 MCP 서버 추가 가이드
├── LICENSE # Apache 2.0
└── pyproject.toml # UV workspace 설정
개발된 MCP 서버 예시
패키지 구조 예시: nps-business-enrollment
src/nps-business-enrollment/
├── pyproject.toml # 패키지 메타데이터 및 의존성
├── data_go_mcp/
│ └── nps_business_enrollment/ # 모듈명은 하이픈(-) 대신 언더스코어(_) 사용
│ ├── __init__.py
│ ├── server.py # MCP 서버 엔트리포인트
│ ├── api_client.py # data.go.kr API 호출 로직
│ └── models.py # Pydantic 모델 정의
└── tests/
├── __init__.py
├── test_api_client.py # API 클라이언트 단위 테스트
└── test_models.py # 데이터 모델 검증 테스트
중요: 패키지명은 하이픈(-) 사용, 모듈명은 언더스코어(_) 사용
개발 환경 설정
필수 도구
- Python 3.10+
- UV (패키지 매니저)
설치
# 의존성 설치
uv sync --dev
# 특정 서버 개발
cd src/nps-business-enrollment
uv sync
새로운 MCP 서버 추가하기
1. Cookiecutter로 템플릿 생성
# 프로젝트 루트에서 실행
uv run cookiecutter template/ -o src/
# 프롬프트 입력 예시:
# api_name: Weather Forecast # 사람이 읽기 쉬운 이름
# api_slug: weather-forecast # URL/디렉토리용 (자동 생성됨)
# package_name: data-go-mcp.weather-forecast # PyPI 패키지명 (자동 생성됨)
# module_name: weather_forecast # Python 모듈명 (자동 생성됨)
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.
- 6d ago First seen · 242 lines · 1,926 tokens per session scan A ebbbafd29706
data-go-mcp-servers CLAUDE.md is an instructions file published in the GitHub repository Koomook/data-go-mcp-servers (296 stars, last pushed 11mo ago), licensed Apache-2.0. It adds 1,926 tokens to every session, about $0.0096 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 2026-08-30.
Other instructions, from other repositories
vibe-coding-prompt-template backend.instructions.md
Instructions for KhazP/vibe-coding-prompt-template: Read AGENTS.md, agentdocs/techstack.md, and agentdocs/codepatterns.md.
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).
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.