Borrowing it
Nothing to install: this file belongs to hlucent/air-emission-facility-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.
curl -O https://raw.githubusercontent.com/hlucent/air-emission-facility-mcp/master/CLAUDE.mdgit clone --depth 1 https://github.com/hlucent/air-emission-facility-mcpWrote 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/hlucent/air-emission-facility-mcp/claude-md)<a href="https://agentmods.dev/instructions/hlucent/air-emission-facility-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hlucent/air-emission-facility-mcp/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 | $0.05090 | $0.05090 |
| Opus 5 | $0.02545 | $0.02545 |
| Sonnet 5 | $0.01018 | $0.01018 |
| Haiku 4.5 | $0.00509 | $0.00509 |
Grade A, and why
air-emission-facility-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 7d 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.
curl -X POST http://localhost:8000/mcp/initialize \ How it starts
The opening of the file, as written. The whole thing — 613 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code 실행 지침 — air-emission-facility-mcp
절대 규칙
- DEVPLAN.md 하나만 읽고 시작. 다른 문서 재탐색 금지.
- 웹 검색 금지. API 스펙은 DEVPLAN.md에 이미 있음.
- 불확실하면 추측성 재설계 대신 기본값 1개로 구현 후 DEVLOG.md에 "확인 필요" 기록.
- 동일 오류 최대 3회까지만 재시도. 3회 실패 시 기록하고 사용자에게 보고.
- Claude Code의 역할은 "코드 구현 + 로컬 실측 테스트"까지.
fly launch/fly secrets set/flyctl deploy등 fly.io 관련 명령은 절대 자동 실행 금지.- 배포는 사용자가 PowerShell에서 직접 수행함.
- 로컬 테스트까지 마친 후 아래 "작업 완료" 섹션 안내 문구 그대로 출력하고 정지.
기술적 필수 사항
.env 파일 처리 (BOM 문제 방지)
.env 파일을 생성하거나 갱신할 때 **반드시 UTF-8 (BOM 없음)**으로 저장한다.
# python-dotenv가 BOM을 읽지 못하는 문제 방지
# .env 값을 생성/갱신할 때:
import os
env_content = f"SEOUL_AIR_EMISSION_API_KEY={api_key}\n"
# ❌ 틀린 방법:
# with open('.env', 'w') as f:
# f.write(env_content) # Python 기본값이 BOM을 붙일 수 있음
# ✅ 올바른 방법:
with open('.env', 'w', encoding='utf-8') as f:
f.write(env_content)
stateless_http=True 필수
server.py의 mcp.run() 호출에 반드시 이 옵션을 포함한다:
mcp.run(
transport="streamable-http",
host="0.0.0.0",
port=port,
stateless_http=True # ← 절대 빼지 말 것
)
이유: fly.io는 기본적으로 머신 2대(HA)를 띄우는데, streamable-http 세션이 프로세스 메모리에만 저장되면 다른 머신이 요청을 받을 때 세션을 모르고 404를 반환한다. 이 옵션 없이 배포하면 Claude.ai 커넥터에서 "사용 가능한 도구 없음" 오류가 발생한다.
API 키 취급 원칙
- 실제 키 값은 코드에 하드코딩하지 않음.
os.environ으로만 읽기. .env파일을 갱신했다는 사용자 보고 후 재테스트하기 전에, 반드시 파일이 실제로 갱신됐는지 확인할 것.- 파일 크기(바이트), 값의 앞 몇 글자 등으로 이전과 달라졌는지 비교.
- 과거: 사용자가 "갱신했다"고 했으나 실제로는 파일이 그대로여서 같은 오류가 여러 번 반복된 사례 있음.
rate limit 미들웨어 (3단계)
이 MCP는 API 키 없이 공개되므로 반드시 아래 3단계 IP 기반 rate limit을 구현한다.
# server.py 상단에 미들웨어 로직 포함
# 1단계: 분당 호출 제한 (슬라이딩 윈도우)
# - 같은 IP에서 60초 내 3회 초과 → 429 반환
# 2단계: 반복 위반 차단
# - 1시간 내 429 응답 5회 이상 → 해당 IP 24시간 차단
# 3단계: 일일 총량 제한
# - IP당 24시간(rolling) 기준 총 30회 초과 → 429 반환
# 구현 원칙:
# - 저장: in-memory dict/map (서버 재시작 시 초기화 허용)
# - IP 추출: X-Forwarded-For 헤더 (fly.io 프록시 환경) 또는 remote_addr
# - 응답: 429 + "Rate limit exceeded" 메시지
# - 다른 머신의 카운터와 완벽히 동기화되지 않아도 무방 (근사값 허용)
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.
- 7d ago First seen · 613 lines · 5,090 tokens per session scan A 9f8ca2740a3a
air-emission-facility-mcp CLAUDE.md is an instructions file published in the GitHub repository hlucent/air-emission-facility-mcp (0 stars, last pushed 15d ago), licensed MIT. It adds 5,090 tokens to every session, about $0.0255 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 2026-08-31.
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.
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.