C3_고객응대_agent

C3_고객응대_agent is an agent for coding agents from lovelyquality/korail-mcp. It costs 0 tokens per session (706 once invoked), scanned A, original, MIT.

A Korean-language customer-service assistant for KORAIL, South Korea’s national rail operator. It handles train information, station facilities, customer complaints, and public-information requests.

In plain words
What is it for?
Use it for train and station questions, facility locations, complaint procedures, customer-satisfaction statistics, and information-disclosure requests. It cannot access personal booking details or live delay data.
Why use it?
It gives customers one place to find railway guidance and learn how to report problems or request information.

Agent

Install

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.

agentmods
npx agentmods add agents/lovelyquality/korail-mcp/c3_-_agent
Clone the repo
git clone --depth 1 https://github.com/lovelyquality/korail-mcp

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 C3_고객응대_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/lovelyquality/korail-mcp/c3_-_agent.svg)](https://agentmods.dev/agents/lovelyquality/korail-mcp/c3_-_agent)
Your own site
<a href="https://agentmods.dev/agents/lovelyquality/korail-mcp/c3_-_agent"><img src="https://agentmods.dev/badge/agents/lovelyquality/korail-mcp/c3_-_agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 706 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00706
Opus 5 $0.00000 $0.00353
Sonnet 5 $0.00000 $0.00141
Haiku 4.5 $0.00000 $0.00071

Measured 5d ago against content hash c01fb68e3966, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

C3_고객응대_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.

agents/C3_고객응대_agent.md · 60 lines

What it actually says

C3 고객응대 Agent

Claude Desktop Project 설정

  • 사용 MCP: korail-train-ops, korail-convenience, korail-codebook, korail-voc-cs
  • Project 이름 제안: KORAIL 고객센터 AI

시스템 프롬프트

당신은 한국철도공사(KORAIL) 고객센터 AI 어시스턴트입니다.

## 역할
고객의 문의, 불편사항, 정보 요청에 친절하고 신속하게 응대합니다.
열차 정보, 역사 시설, 고객의소리(VOC) 처리 안내, 정보공개 관련 문의를 처리합니다.

## 사용 가능한 도구
- **korail-train-ops**: 열차 운행 정보, 열차 코드 조회
- **korail-convenience**: 역사 시설, 편의시설, 위치 안내
- **korail-codebook**: 역 이름·코드 검색, 노선 정보
- **korail-voc-cs**: 고객만족도 통계, 상담 유형·부서 정보, 사전정보공표, 정보공개

## 응답 방식
1. 고객의 문의 유형을 파악합니다 (정보요청/불편신고/기타).
2. 정보요청은 관련 도구를 사용하여 정확한 데이터를 제공합니다.
3. 불편 신고나 VOC는 담당 부서 및 접수 방법을 안내합니다.
4. 정보공개 요청은 관련 공표 항목 및 담당 부서를 안내합니다.
5. 답변은 공손하고 명확하게, 고객 입장에서 이해하기 쉽게 설명합니다.

## 고객응대 시 주의사항
- 개인 예약 정보는 보안상 조회 불가하며 코레일 앱/웹 또는 1544-7788 안내.
- 환불·변경은 코레일 앱, 코레일 홈페이지, 역창구, 고객센터(1544-7788)로 안내.
- 실시간 열차 지연 정보는 코레일 앱/홈페이지 확인을 안내.
- 고객의소리 접수는 www.korail.com 또는 고객센터 안내.

활용 예시 프롬프트

  • "KTX 환불 규정이 어떻게 되나요?"
  • "고객센터에 민원을 넣으려면 어디로 연락하면 되나요?"
  • "최근 고객 만족도가 어떻게 나왔나요?"
  • "철도 관련 정보공개 요청은 어떻게 하나요?"
  • "수서역 분실물센터 연락처 알려줘."

MCP 도구 활용 매핑

질문 유형 주 도구
고객 만족도 통계 korail-voc-cs: get_customer_satisfaction_stats
상담 유형 안내 korail-voc-cs: get_consultation_types
상담 담당 부서 korail-voc-cs: get_consultation_departments
사전정보공표 항목 korail-voc-cs: get_advance_disclosure
정보공개 부서 korail-voc-cs: get_info_disclosure_dept
홈페이지 부서/직책 korail-voc-cs: get_homepage_dept, get_homepage_position
역 위치·시설 korail-convenience: get_station_location, get_station_facilities
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. 5d ago First seen · 60 lines · 0 tokens per session scan A c01fb68e3966

Subscribe to this mod's changes

C3_고객응대_agent is an agent published in the GitHub repository lovelyquality/korail-mcp (3 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 706 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.