transit-mcp
MCP server for Korean public transit that enables route planning with real-time bus and subway arrivals, including fallback options. It combines ODsay route search with real-time data from Gyeonggi Bus and Seoul Metro systems.
README
transit-mcp — 이동비서 MCP (Korean Public Transit MCP Server)
A remote MCP (Model Context Protocol) server for Korean public transit. It helps an AI assistant answer not just "how do I get there?" but "what should I take right now, and what's my fallback if I miss it?" — combining route planning with real-time bus and subway arrivals.
Built for the Streamable HTTP transport with the official
@modelcontextprotocol/sdk, stateless
and container-ready.
Tools
| Tool | What it does | Data source |
|---|---|---|
search_route |
Plan a transit route between two places: fastest route with per-leg detail (lines, stops, boarding-stop IDs), total fare, and condition-best alternatives (fewest transfers / cheapest / least walking). | ODsay(오디세이) + keyword geocoding |
get_bus_arrival |
Real-time bus arrivals at a stop (by name or stop ID): minutes away, stops away, remaining seats, crowding, low-floor; falls back to route headway + last-bus time. | Gyeonggi Bus(경기버스) |
get_subway_arrival |
Real-time subway arrivals at a station (whole Seoul metro network), with optional line filter: destination/direction, minutes away, current train position. | Seoul Metro(서울 지하철) |
Boarding-stop IDs from search_route chain directly into get_bus_arrival, so an
assistant can go from "plan the route" to "is the next bus coming in time?" in one flow.
Endpoint
- Transport: Streamable HTTP (stateless)
- Path:
POST /mcp - Health check:
GET /health - Protocol version:
2025-03-26
Running locally
npm install
cp .env.example .env # fill in the API keys
npm run build
npm start # serves on :8080/mcp
Or in dev mode with reload:
npm run dev
Docker
docker build --platform linux/amd64 -t transit-mcp .
docker run --env-file .env -p 8080:8080 transit-mcp
Environment variables
| Variable | Purpose |
|---|---|
KAKAO_REST_KEY |
Local keyword geocoding (place → coordinates) |
ODSAY_API_KEY |
ODsay public-transit route search |
ODSAY_REFERER |
Referer header required by the domain-registered ODsay key |
GYEONGGI_BUS_SERVICE_KEY |
Gyeonggi bus real-time arrivals |
SEOUL_SUBWAY_ARRIVAL_KEY |
Seoul subway real-time arrivals |
PORT |
HTTP port (default 8080) |
Coverage & notes
- Route search covers the Seoul metropolitan area.
- Real-time bus data covers Gyeonggi Province stops (Seoul city buses are a planned addition via a nationwide bus API).
- Real-time subway data covers the entire Seoul metropolitan subway network.
- Tool responses are curated Korean text (not raw API dumps) to stay compact.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.