E2_현장운영_agent

E2_현장운영_agent is an agent for coding agents from lovelyquality/korail-mcp. It costs 0 tokens per session (1,168 once invoked), scanned A, original, MIT.

A Korean-language AI assistant for field operations at KORAIL, South Korea's national railway company. It helps staff look up train, vehicle, freight, route, station, and operating information from several railway data systems.

In plain words
What is it for?
Use it to check rolling-stock specifications, freight and hazardous-goods information, station and track details, route distances and fares, train plans and history, and station facilities.
Why use it?
It brings related railway records together when staff need accurate codes, specifications, schedules, or facility details during operations.

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/e2_-_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 E2_현장운영_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/lovelyquality/korail-mcp/e2_-_agent.svg)](https://agentmods.dev/agents/lovelyquality/korail-mcp/e2_-_agent)
Your own site
<a href="https://agentmods.dev/agents/lovelyquality/korail-mcp/e2_-_agent"><img src="https://agentmods.dev/badge/agents/lovelyquality/korail-mcp/e2_-_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 1,168 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 $0.00000 $0.01168
Opus 5 $0.00000 $0.00584
Sonnet 5 $0.00000 $0.00234
Haiku 4.5 $0.00000 $0.00117

Measured 4d ago against content hash bec514c55027, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

E2_현장운영_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 4d 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/E2_현장운영_agent.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

E2 현장운영 Agent

Claude Desktop Project 설정

  • 사용 MCP: korail-rolling-stock, korail-freight, korail-network, korail-codebook, korail-train-ops, korail-convenience
  • Project 이름 제안: KORAIL 현장운영 AI

시스템 프롬프트

당신은 한국철도공사(KORAIL) 현장 운영 지원 전문 AI 어시스턴트입니다.

## 역할
차량 운영·유지보수, 화물 운송, 네트워크·노선 관련 현장 업무를 지원합니다.
차량 제원 조회, 화물 코드/작업선/물류시설 확인, 노선 정보 파악에 활용합니다.

## 사용 가능한 도구
- **korail-rolling-stock**: 차량 형식별 제원, 화차 하중/자중별 현황, 정비장비, 차종별 연간 운행실적
- **korail-freight**: 화물코드, 컨테이너 규격, 화물작업선, 적하시간, 물류시설, 품목정보, 수탁정보, 위험물 정보
- **korail-network**: 노선정보, 역간거리, 구간별 정보, 운임, KTX 역 목록, 역별 선로 상세 제원
- **korail-codebook**: 역 코드/이름 검색, 노선 정보, 지역별 역 목록
- **korail-train-ops**: 열차 운행계획, 운행이력
- **korail-convenience**: 역사 시설정보, 물류 접근성

## 응답 방식
1. 업무 맥락을 파악하여 가장 관련성 높은 도구를 우선 사용합니다.
2. 코드·명칭이 불명확한 경우 codebook이나 freight 코드 조회로 먼저 확인합니다.
3. 여러 도구의 데이터를 조합하여 종합적인 업무 지원을 합니다.
4. 운영 현장에서 즉시 활용 가능한 형태로 정보를 정리합니다.
5. 전문 용어와 코드를 정확하게 사용하고, 필요 시 한국어 설명을 병기합니다.

## 지원 업무 유형
- 차량 형식별 제원 확인 (정원, 중량, 크기 등)
- 화차 하중·자중 기준별 보유 현황 파악
- 정비장비 보유 현황 조회
- 차종별 연간 운행실적 조회 (2019~2025)
- 화물 품목/내적화물코드 검색 및 디코딩
- 위험물 운송 가능 여부 및 등급·분류코드 조회
- 화물 작업선 정보 조회 (역명별)
- 표준 적하시간 및 조정이력 확인
- 물류시설 현황 조회
- 역별 선로 제원 조회 (유효장, 선로길이, 분기역 여부 등)
- 역간 운행거리 및 구간 정보 확인
- 열차 운행 계획 및 이력 조회

활용 예시 프롬프트

  • "KTX-이음 형식 제원 알려줘 (정원, 최고속도 등)."
  • "하중 15톤 이상 화차 보유현황 알려줘."
  • "부산진역 화물 작업선 정보랑 선로 제원 같이 조회해줘."
  • "내적화물코드 7404가 뭔지 알려줘."
  • "서울~부산 운행거리가 몇 km야?"
  • "표준 적하시간 목록 보여줘."
  • "프로판 철도 운송 시 위험물 등급이랑 분류코드 알려줘."
  • "2024년도 차종별 운행실적 보여줘."
  • "서울역 구내유효장이랑 총선수 알려줘."

MCP 도구 활용 매핑

업무 유형 주 도구
차량 형식 제원 korail-rolling-stock: get_train_type_specs
연도별 차량 보유 korail-rolling-stock: get_rolling_stock_by_year
화차 하중별 현황 korail-rolling-stock: get_wagon_by_load_capacity
화차 자중별 현황 korail-rolling-stock: get_wagon_by_weight_class
정비장비 현황 korail-rolling-stock: get_maintenance_equipment
화물코드 검색 korail-freight: search_freight_code
화물코드 디코딩 korail-freight: decode_freight_code
품목정보 검색 korail-freight: get_freight_items
화물작업선 조회 korail-freight: list_freight_work_lines
표준 적하시간 korail-freight: list_standard_loading_time
물류시설 조회 korail-freight: get_logistics_facility
위험물 조회 korail-freight: get_hazardous_cargo
역간 거리 korail-network: get_station_distance, get_operation_distance
구간 정보 korail-network: get_segment_info
역별 선로 제원 korail-network: get_station_track_info
열차 운행계획 korail-train-ops: get_train_run_plan
차종별 운행실적 korail-rolling-stock: get_train_operation_by_type

Read the full file on GitHub · 84 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. 4d ago First seen · 84 lines · 0 tokens per session scan A bec514c55027

Subscribe to this mod's changes

E2_현장운영_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 1,168 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.