Borrowing it
Nothing to install: this file belongs to SongHyojun0228/opendart-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.
curl -O https://raw.githubusercontent.com/SongHyojun0228/opendart-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/SongHyojun0228/opendart-mcp-serverWrote 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/songhyojun0228/opendart-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/songhyojun0228/opendart-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/songhyojun0228/opendart-mcp-server/claude-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.
<a href="https://agentmods.dev/instructions/songhyojun0228/opendart-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/songhyojun0228/opendart-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.04362 | $0.04362 |
| Opus 5 | $0.02181 | $0.02181 |
| Sonnet 5 | $0.00872 | $0.00872 |
| Haiku 4.5 | $0.00436 | $0.00436 |
Grade A, and why
opendart-mcp-server 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 9d 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — OpenDART MCP Server
이 파일은 AI 코딩 어시스턴트(Claude Code, Cursor 등)가 프로젝트를 이해하기 위한 마스터 문서입니다. 코드를 작성하기 전에 반드시 이 파일 전체를 읽으세요.
🎯 프로젝트 한 줄 요약
한국 금융감독원 DART(전자공시시스템) 데이터를 AI 에이전트가 사용할 수 있게 하는 MCP 서버.
"삼성전자 최근 3년 매출 추이 알려줘", "카카오 최대주주가 누구야?", "오늘 공시 나온 거 있어?" 같은 질문에 AI가 직접 DART API를 호출해 답할 수 있게 만든다.
📦 프로젝트 정보
- 이름:
opendart-mcp-server - npm 패키지명:
opendart-mcp(추후 배포 시) - 언어: TypeScript
- 런타임: Node.js 18+
- 프레임워크: FastMCP (TypeScript) —
npm i fastmcp - 라이선스: MIT
🏗️ 프로젝트 구조
opendart-mcp-server/
├── src/
│ ├── index.ts # 진입점 — FastMCP 서버 초기화 + 시작
│ ├── tools/ # MCP Tool 정의 (DART API별 1파일)
│ │ ├── disclosure.ts # 공시검색, 기업개황, 고유번호
│ │ ├── financial.ts # 재무제표, 주요계정, 재무지표
│ │ ├── shareholder.ts # 최대주주, 지분공시, 임원현황
│ │ └── event.ts # 주요사항보고서 (유상증자, 합병 등)
│ ├── utils/
│ │ ├── dart-client.ts # DART API HTTP 클라이언트 (인증키 관리, 요청, 에러 처리)
│ │ ├── corp-code.ts # 회사명/종목코드 → DART 고유번호 변환 유틸리티
│ │ └── formatters.ts # 숫자 포맷팅, 날짜 변환, 응답 정리 헬퍼
│ └── types/
│ └── dart.ts # DART API 응답 타입 정의
├── data/
│ └── corp-codes.json # DART 고유번호 ↔ 회사명/종목코드 매핑 캐시 (빌드 시 생성)
├── scripts/
│ └── update-corp-codes.ts # DART에서 최신 고유번호 목록 다운로드하는 스크립트
├── package.json
├── tsconfig.json
├── .env.example # DART_API_KEY=your_key_here
├── .gitignore
├── README.md # 사용자 대상 설명서 (한국어 + 영어)
├── CLAUDE.md # 이 파일
└── BRAND.md # 브랜드 가이드
🔧 기술 스택 상세
FastMCP (TypeScript)
- GitHub: https://github.com/punkpeye/fastmcp
- npm:
fastmcp(최신 버전 사용) - 이유: MCP 서버 구축에 가장 적은 보일러플레이트.
server.addTool()로 도구 정의가 끝남 - 전송 방식:
stdio(Claude Desktop/Cursor 용) +httpStream(원격 접속 용)
DART OpenAPI
- 공식 사이트: https://opendart.fss.or.kr
- 인증: API Key (무료 발급, 일 10,000건 제한)
- 응답 형식: JSON (기본) 또는 XML
- Base URL:
https://opendart.fss.or.kr/api/
📡 DART OpenAPI 사용할 엔드포인트 목록
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.
- 9d ago First seen · 363 lines · 4,362 tokens per session scan A 025eed8ba0cd
opendart-mcp-server CLAUDE.md is an instructions file published in the GitHub repository SongHyojun0228/opendart-mcp-server (2 stars, last pushed 6mo ago), licensed MIT. It adds 4,362 tokens to every session, about $0.0218 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 2026-08-31.
Other instructions, from other repositories
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.