scienceON-mcp: Instructions file for Claude Code

CLAUDE.md

scienceON-mcp CLAUDE.md is an instructions file for Claude Code from rubatoyd/scienceON-mcp. It costs 6,658 tokens per session, scanned A, original, MIT.

A set of project instructions for scienceon-mcp, a tool that searches KISTI ScienceON for papers and reports and collects their bibliographic details. It covers the project’s structure, credentials, outputs, and development setup.

In plain words
What is it for?
Use it when developing or maintaining scienceon-mcp, searching ScienceON, collecting publication or report records, or exporting results as XLSX, CSV, JSON, or SQLite data.
Why use it?
It gives an agent the rules needed to work consistently in that project. It explains how searches, metadata collection, authentication, and exported files are organised.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

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

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is name="../escaped" → …\Temp\<tmp>\escaped.json ← out_dir 밖.

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rubatoyd/scienceon-mcp/claude-md.svg)](https://agentmods.dev/instructions/rubatoyd/scienceon-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rubatoyd/scienceon-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/rubatoyd/scienceon-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,658 This file is loaded in full into every session.
When invoked 6,658 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 $0.06658 $0.06658
Opus 5 $0.03329 $0.03329
Sonnet 5 $0.01332 $0.01332
Haiku 4.5 $0.00666 $0.00666

Measured 8d ago against content hash b68b226db6f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

scienceON-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 8d 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.

CLAUDE.md · 242 lines

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.

scienceon-mcp — 프로젝트 지침

KISTI ScienceON OpenAPI 문헌 검색·메타데이터 수집기. 누구나 자기 API 키로 쓰는 공개 MCP 서버 + CLI. API 호출 규격은 docs/SCIENCEON_API_GUIDE.md 참조.

1. 목표

연구 초반 자료수집 단계에서 반복 재사용하는 도구. 논문·보고서 등 서지 메타데이터를 검색·수집해 후속 텍스트마이닝 입력 데이터를 안정적으로 생산한다.

2. 확정 결정사항

항목 결정
언어/런타임 Python 3.10+ (개발 venv는 3.12)
패키지 관리 uv (pyproject + uv.lock). venv는 클라우드 폴더 밖 C:\Users\user\.venvs\scienceon-mcp (UV_PROJECT_ENVIRONMENT, .claude/settings.local.json 에 지정)
의존성 mcp(FastMCP), requests, pycryptodome, openpyxl, python-dotenv, pyyaml
인터페이스 공용 코어 + MCP 서버(server.py) + CLI(cli.py)
수집 대상 ARTI(논문)·REPORT(보고서) 우선, ATT/RESEARCHER/ORGAN 확장 가능
출력 xlsx · csv · json · sqlite
공개 MIT. .env·reference/·output/·토큰캐시는 gitignore

3. 구조

src/scienceon_mcp/
  config.py     # .env 로딩, 엔드포인트
  auth.py       # AES256 토큰 발급/캐시/갱신 (라이브 검증 완료)
  client.py     # 검색/상세/페이징/재시도/에러
  parser.py     # XML(.//record/item[@metaCode]) → 정규화
  models.py     # Record 스키마
  exporters.py  # xlsx/csv/json/sqlite
  server.py     # MCP 도구: scienceON_search/detail/export/status
  cli.py        # status/search/detail/collect
docs/           # API 가이드, 워크플로, 프롬프트
config/         # 검색 설정 템플릿
reference/      # KISTI 매뉴얼·공식 샘플(gitignore, 비공개)

4. 자격증명 (.env 또는 사용자 환경변수)

  • 변수: SCIENCEON_AUTH_KEY(32자), SCIENCEON_CLIENT_ID, SCIENCEON_MAC_ADDRESS, SCIENCEON_ACCOUNT_ID
  • 구독 티켓(계정별 상이): 예) ARTI·REPORT·ATT·RESEARCHER·ORGAN
  • API Gateway IP관리에 호출 PC 공인 IP 등록·활성화 필수(미등록 시 E4006). MAC = 신청 시 등록한 대표 MAC.
  • ⚠️ 인증키는 코드/로그/커밋 금지 — .env(gitignore) 또는 OS 사용자 환경변수로만.

5. 핵심 기술사실 (라이브 검증)

  • 토큰 발급: tokenrequest.do?client_id=&accounts= — accounts = urlsafe_b64( AES-256-CBC( key=인증키 UTF-8 32B, IV=jvHJ1EFA0IXBrxxz(고정), PKCS7, 평문 {"datetime":"YYYYMMDDHHMMSS","mac_address":"..."})) → URL 인코딩. (그 고정 IV는 공식 샘플로만 확인 가능했음)
  • 데이터 호출: openapicall.do?...&action=search|browse&target=ARTI&searchQuery={"BI":"검색어"}&curPage=&rowCount=
  • 응답 XML: 레코드 .//record, 필드 <item metaCode="...">. 총건수 TotalCount. ARTI metaCode: CN/Title/Author/Pubyear/Publisher/JournalName/Abstract/Keyword/DOI/ContentURL.
  • Access Token 2시간, Refresh Token 2주. 429(Too Many Requests) 주의 → throttle·백오프 필수.

Read the full file on GitHub · 242 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. 8d ago First seen · 242 lines · 6,658 tokens per session scan A b68b226db6f7

Subscribe to this mod's changes

scienceON-mcp CLAUDE.md is an instructions file published in the GitHub repository rubatoyd/scienceON-mcp (1 stars, last pushed yesterday), licensed MIT. It adds 6,658 tokens to every session, about $0.0333 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.

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

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

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