korean-dart-mcp: Instructions file for Claude Code

CLAUDE.md

korean-dart-mcp CLAUDE.md is an instructions file for Claude Code from chrisryugj/korean-dart-mcp. It costs 823 tokens per session, scanned A, original, MIT.

A project guide for korean-dart-mcp, an MCP server that gives AI tools access to OpenDART, South Korea’s corporate disclosure service. It describes the code structure and design rules, including finding companies and grouping many financial-reporting operations into simpler tools.

In plain words
What is it for?
It is for developing features such as company lookup, disclosure search, company information, financial data, and access to original XBRL files. XBRL is a machine-readable format for financial reports.
Why use it?
It gives coding agents the project-specific information they need to change the server consistently and avoid editing generated code or duplicating tools.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is chrisryugj/korean-dart-mcp's own configuration. It tells Claude Code how to work on korean-dart-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 korean-dart-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chrisryugj/korean-dart-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/chrisryugj/korean-dart-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chrisryugj/korean-dart-mcp

Made for: Claude Code.

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 korean-dart-mcp CLAUDE.md

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

agentmods 80×15 button for korean-dart-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chrisryugj/korean-dart-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrisryugj/korean-dart-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 823 This file is loaded in full into every session.
When invoked 823 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 $0.00823 $0.00823
Opus 5 $0.00411 $0.00411
Sonnet 5 $0.00165 $0.00165
Haiku 4.5 $0.00082 $0.00082

Measured 11d ago against content hash 331364098df6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

korean-dart-mcp 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 11d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 73 lines

What it actually says

korean-dart-mcp 프로젝트 가이드

OpenDART(금융감독원 전자공시) 를 MCP 서버로 래핑. korean-law-mcp(법제처) 와 자매 프로젝트.

구조

src/
├── index.ts              # MCP stdio 서버 진입점
├── cli.ts                # CLI 진입점 (korean-dart 명령어)
├── version.ts
├── lib/
│   ├── dart-client.ts    # OpenDART HTTP 클라이언트 (JSON/ZIP)
│   └── corp-code.ts      # corp_code 리졸버 (SQLite FTS)
├── server/
│   └── mcp-server.ts     # MCP Server 팩토리
├── tools/
│   └── index.ts          # 15개 도구 레지스트리
└── utils/

설계 원칙

1. corp_code 자동 해결

  • LLM은 "삼성전자"만 알고, 모든 OpenDART API는 corp_code 8자리 필수
  • 해결: 서버 기동 시 /api/corpCode.xml 전체 덤프(≈10만개) SQLite FTS 로 선적재
  • 캐시 경로: ~/.korean-dart-mcp/corp_code.sqlite (없거나 24시간 지나면 재다운)

2. enum 으로 도구 폭발 방지

  • OpenDART 83개 → MCP 15개
  • 정기보고서 28개 → get_periodic_report({ report_type: "executive_compensation" })
  • 주요사항 36개 → get_corporate_event({ event_type: "merger" })
  • 참고: korean-law-mcp 에서 41→15 압축한 동일 패턴

3. XBRL 원본 노출

  • get_xbrl 은 파싱하지 않고 원본 XBRL 파일을 그대로 반환
  • Claude 가 직접 업로드 받아 임의 집계 → 기존 Python 래퍼(OpenDartReader, dart-fss)가 놓친 LLM 시너지 포인트

구현 우선순위

P0 (동작 확인용 MVP):

  1. resolve_corp_code
  2. search_disclosures
  3. get_company
  4. get_financials

P1 (문서 + XBRL): 5. download_document 6. get_full_financials 7. get_xbrl 8. get_periodic_report

P2 (심화): 9-12. 보수/주주/지분/주요사항

P3 (배치·비교): 13-15. 증권신고·최근 공시·비교

OpenDART 규칙

  • Base URL: https://opendart.fss.or.kr/api/
  • 인증: 모든 요청에 crtfc_key 쿼리파라미터
  • 응답: JSON (대부분), ZIP (corp_code 덤프·원문·XBRL)
  • 요율: 일 20,000건 (키 단위 합산)
  • 원문 포맷: DART XML (전용 마크업), HWP/PDF 원본은 attach_files() 별도

참고

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. 11d ago First seen · 73 lines · 823 tokens per session scan A 331364098df6

Subscribe to this mod's changes

korean-dart-mcp CLAUDE.md is an instructions file published in the GitHub repository chrisryugj/korean-dart-mcp (98 stars, last pushed 1mo ago), licensed MIT. It adds 823 tokens to every session, about $0.0041 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens