Seoul Mobility Advisor
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Seoul Mobility AdvisorWhat's the best way to get from Gangnam to Myeongdong considering weather and traffic?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Seoul Mobility Advisor (mobility-mcp)
카카오 PlayMCP 공모전 출품작 — 날씨·대기질·실시간 교통·따릉이 데이터와 **사진(시각 맥락)**을 종합해 상황에 맞는 이동수단(도보/따릉이/대중교통/자가용)을 추천하는 MCP 서버.
설계 원칙
서버는 '데이터 + 결정론적 도구'만 제공한다. 자연어/이미지 해석과 추천 판단은
**호스트 LLM(PlayMCP AI / Claude)**이 담당한다. 사진 분석도 호스트가 수행해
constraints 태그(예: cannot_ride_bike, formal_attire)로 툴에 넘긴다.
Related MCP server: OpenAPI Korea MCP Server
빠른 시작
uv sync --extra dev # 의존성 설치
cp .env.example .env # (선택) 키 입력 — 키 없어도 mock으로 동작
uv run mobility-mcp # 로컬 실행 (stdio)MCP Inspector로 점검
npx @modelcontextprotocol/inspector uv run mobility-mcp원격 실행 (PlayMCP 등록/배포용, Streamable HTTP)
MCP_TRANSPORT=http uv run mobility-mcp # → http://localhost:8000/mcp/테스트
uv run --extra dev pytest현재 툴 (Phase 1)
툴 | 설명 |
| 서울 따릉이 실시간 대여가능 수 (키 없으면 샘플) |
로드맵
~/.claude/plans/temporal-drifting-peacock.md 참고.
Phase 2 날씨/대기/교통 클라이언트 · Phase 3 compare_transport_options 점수엔진 · Phase 4–5 Docker→KC 배포·PlayMCP 등록.
구조
src/mobility_mcp/
server.py # FastMCP 앱 + 툴
config.py # .env 키 로딩
clients/seoul_bike.py# 따릉이 클라이언트(+mock)
tests/This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/todayoneul/mobility-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server