ÖPNV MCP Server
MCP server for querying German public transport information, including station search, live departures/arrivals, and journey planning.
README
ÖPNV MCP Server
A Model Context Protocol (MCP) server for German public transport information using the v6.db.transport.rest API.
Features
- Search stations and stops - Find train stations, bus stops, tram stops across Germany
- Live departures/arrivals - Real-time information with delay tracking
- Journey planning - Find connections with transfers, platform info, and tight connection warnings
- Smart warnings - Highlights delays, cancellations, platform changes, and risky transfers
Supports all transport types: ICE, IC, RE, RB, S-Bahn, U-Bahn, Tram, Bus
Installation
npm install
npm run build
Usage
Add to your MCP client configuration. This server uses stdio transport.
Example configuration:
{
"mcpServers": {
"oepnv": {
"command": "node",
"args": ["/absolute/path/to/oepnv-mcp/dist/index.js"]
}
}
}
Restart your MCP client to activate the server.
Example Queries
- "Find trains from München Hbf to Berlin"
- "Show me departures from Alexanderplatz"
- "When does the next S-Bahn leave from Marienplatz?"
- "Plan a journey from Stuttgart to Hamburg tomorrow at 10:00"
Available Tools
search_station
Search for stations and stops by name.
Parameters:
query(string): Station name (e.g., "München Hbf", "Berlin Alexanderplatz")
get_departures
Get live departures from a station.
Parameters:
stationId(string): Station ID from search resultsduration(number, optional): Time window in minutes (default: 90, max: 120)
get_arrivals
Get live arrivals at a station.
Parameters:
stationId(string): Station ID from search resultsduration(number, optional): Time window in minutes (default: 90, max: 120)
search_journeys
Find journey connections between two stations.
Parameters:
originId(string): Origin station IDdestinationId(string): Destination station IDdepartureTime(string, optional): Departure time inYYYY-MM-DDTHH:MMformat
Development
# Run in development mode
npm run dev
# Build
npm run build
# Start production server
npm start
API
This server uses the v6.db.transport API (db-vendo-client as backend).
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。