archhub-mcp: Instructions file for Claude Code

CLAUDE.md

archhub-mcp CLAUDE.md is an instructions file for Claude Code from chrisryugj/archhub-mcp. It costs 1,592 tokens per session, scanned A, original, MIT.

Project instructions for archhub-mcp, a Python server that exposes South Korean public building and land data through tools that coding agents can call. They document the project structure, design decisions, checks, and deployment process.

In plain words
What is it for?
Use them when working on the server, its REST client, data formatting, error handling, health checks, or deployment to the production host.
Why use it?
They give an agent the project-specific rules needed to change, verify, and deploy the server safely. They also explain that the production service runs from a shared host rather than this repository directly.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chrisryugj/archhub-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrisryugj/archhub-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,592 This file is loaded in full into every session.
When invoked 1,592 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.01592 $0.01592
Opus 5 $0.00796 $0.00796
Sonnet 5 $0.00318 $0.00318
Haiku 4.5 $0.00159 $0.00159

Measured 9d ago against content hash 20ee174b4114, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

archhub-mcp CLAUDE.md scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

> - **반영 절차**: 이 레포는 PyPI 미배포 — main에 커밋·푸시한 뒤 `cd ~/workspace/gomdori-mcp && fly deploy -c fly.production.toml` (pip가 GitHub main을 설치) → `curl https://mcp.gomdori.app/healthz` 확인
CLAUDE.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

archhub-mcp — 프로젝트 메모

⚠️ 배포 — 통합 호스트 (2026-07-02부터)

프로덕션 공식 서빙은 gomdori-mcp 통합 호스트(fly 앱 korean-law-mcp 1대, MCP 5종 동거)다.

  • 공식 주소: https://mcp.gomdori.app/archhub (구 앱 archhub-mcp는 통합 완료로 scale 0 처리됨)
  • 반영 절차: 이 레포는 PyPI 미배포 — main에 커밋·푸시한 뒤 cd ~/workspace/gomdori-mcp && fly deploy -c fly.production.toml (pip가 GitHub main을 설치) → curl https://mcp.gomdori.app/healthz 확인
  • 구 앱은 scale 0이므로 이 레포에서 fly deploy 직접 실행은 무의미 — 통합 반영은 반드시 위 절차로
  • 단일 머신 제약(인메모리 캡·세션)은 통합 호스트에서도 유지됨 (fly scale count 1)

국토교통부 건축HUB(공공데이터포털) → MCP 서버. Python + FastMCP 3.x.

구조

archhub/
  __init__.py     # __version__
  __main__.py     # python -m archhub 진입점
  server.py       # FastMCP 인스턴스 + 도구 12개 + /health,/ 라우트 + stdio/http main()
  client.py       # ArchHubClient — 직접 REST 호출 + 법정동코드 캐시 + api_calls 카운터
  errors.py       # [NOT_FOUND]/[ERROR] 포맷 (환각 방지), 키 마스킹
  formatting.py   # DataFrame → 텍스트(종합카드·동단위통계) + 출처 명시

핵심 설계 결정

  • 호출은 직접 REST: PublicDataReader의 get_data()numOfRows=99999 한 방 + timeout 없음 → MCP에 부적합. 그래서 requests로 timeout/numOfRows/pageNo 직접 제어. 엔드포인트는 https로 승격하고 verify=True(평문 http면 키 노출). fetch_all은 행/페이지/총deadline 3중 상한으로 절단.
  • 라이브러리 재활용은 2가지만: meta_dict[type]["url"](엔드포인트 매핑), translate_columns(df)(한글 변환). 단 code_bdong()은 쓰지 않음 — timeout 없고 stdout에 print()(stdio JSON-RPC 오염). 같은 JSON을 timeout 걸어 직접 받아 ~/.cache/archhub-mcp에 캐시(client._load_bdong_json).
  • 공용키 방식: ARCHHUB_SERVICE_KEY 하나로 모든 요청 처리 (BYOK 격리 없음). 공개 remote 보호는 opt-in: ARCHHUB_MCP_TOKEN(Bearer 인증·미설정 시 무인증) + ARCHHUB_DAILY_CALL_CAP(일일 호출 캡).
  • remote 커넥터: fly.io에 streamable-http로 떠서 URL만 등록하면 연결.

검증

# in-memory MCP Client로 도구 목록 + 실호출
ARCHHUB_SERVICE_KEY=... python -c "import asyncio; from fastmcp import Client; from archhub.server import mcp; ..."

# 단위테스트 (외부 API 비의존, mock)
pytest tests/

자양동 = sigungu 11215, bdong 10500 (표제부 totalCount 6057).

Read the full file on GitHub · 66 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. 9d ago First seen · 66 lines · 1,592 tokens per session scan A 20ee174b4114

Subscribe to this mod's changes

archhub-mcp CLAUDE.md is an instructions file published in the GitHub repository chrisryugj/archhub-mcp (65 stars, last pushed 22d ago), licensed MIT. It adds 1,592 tokens to every session, about $0.0080 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

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