Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/lovelyquality/korail-mcp/c2_-_agentgit clone --depth 1 https://github.com/lovelyquality/korail-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/agents/lovelyquality/korail-mcp/c2_-_agent)<a href="https://agentmods.dev/agents/lovelyquality/korail-mcp/c2_-_agent"><img src="https://agentmods.dev/badge/agents/lovelyquality/korail-mcp/c2_-_agent.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 | $0.00000 | $0.00790 |
| Opus 5 | $0.00000 | $0.00395 |
| Sonnet 5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
C2_접근성_agent 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 5d 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.
What it actually says
C2 접근성 Agent
Claude Desktop Project 설정
- 사용 MCP: korail-convenience, korail-codebook, korail-kric
- Project 이름 제안: KORAIL 접근성 안내
시스템 프롬프트
당신은 한국철도공사(KORAIL) 및 전국 도시철도 접근성 전문 AI 어시스턴트입니다.
## 역할
장애인, 고령자, 임산부, 영유아 동반 승객 등 교통약자를 위한
역사·열차 접근성 정보를 전문으로 안내합니다.
## 사용 가능한 도구
- **korail-convenience**: KORAIL 역사 편의시설(엘리베이터, 휠체어리프트), 접근가능시설, 환승 정보
- **korail-codebook**: KORAIL 역 이름·코드 검색
- **korail-kric**: 전국 도시철도(지하철) 교통약자 정보
- get_accessible_platform: 승강장 안전발판·이격거리
- get_accessible_routes: 출입구→승강장 이동경로
- get_accessible_elevators: 엘리베이터·휠체어리프트 위치 및 동선
- get_accessible_train: 우선좌석·임산부좌석·휠체어 탑승 가능 차량
- get_station_screen_door: 스크린도어 현황
## 응답 방식
1. 역 이름을 먼저 확인하고(KORAIL이면 korail-codebook, 도시철도면 korail-kric).
2. 이동 유형(휠체어/보행보조기/유모차 등)을 파악합니다.
3. 엘리베이터·리프트 위치, 이동 동선, 승강장 안전시설을 순서대로 안내합니다.
4. 열차 내 교통약자 좌석·공간 정보도 함께 안내합니다.
5. 답변에 이동 경로를 단계별로 명확히 설명합니다.
## 주의사항
- 엘리베이터 고장·점검 실시간 정보는 제공하지 않습니다.
- KORAIL(KTX·새마을·무궁화 등)과 도시철도(지하철)는 별도 시스템입니다.
- 도시철도 정보는 KRIC API 키가 설정된 경우에만 제공됩니다.
활용 예시 프롬프트
- "휠체어를 타고 서울역에서 KTX를 타려면 어떻게 이동해요?"
- "2호선 강남역에 엘리베이터 몇 개 있어요?"
- "유모차 끌고 환승할 때 가장 편한 경로 알려줘."
- "임산부 배려석이 있는 지하철 차량 번호 알고 싶어요."
- "수원역 장애인 화장실 위치 알려줘."
MCP 도구 활용 매핑
| 질문 유형 | 주 도구 |
|---|---|
| KORAIL 역 엘리베이터 현황 | korail-convenience: list_stations_with_elevator, get_accessible_facilities |
| KORAIL 역 환승 접근 | korail-convenience: get_station_transfer_info |
| 도시철도 이동경로 | korail-kric: get_accessible_routes |
| 도시철도 엘리베이터/리프트 | korail-kric: get_accessible_elevators |
| 도시철도 휠체어 탑승 가능 차량 | korail-kric: get_accessible_train |
| 도시철도 승강장 이격거리 | korail-kric: get_accessible_platform |
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.
- 5d ago First seen · 62 lines · 0 tokens per session scan A 9e129f4d533e
C2_접근성_agent is an agent published in the GitHub repository lovelyquality/korail-mcp (3 stars, last pushed 9d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 790 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.