Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Deutsche Bahn Fahrplan in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Query the Deutsche Bahn (DB) timetable via the community-maintained v6.db.transport.rest proxy over the official HAFAS API. Search stations, look up departures/arrivals in real time, and plan journeys between any two DB stops.
试试这样问
Deutsche Bahn Fahrplan 的示例提示
点击任意提示即可复制，然后粘贴到 Claude、ChatGPT、Cursor、Gemini、Copilot 或 OpenClaw 中，在该连接器上运行。
Claude 是 AI，可能会出错。请核对回答。
💡 无需安装? 直接使用 cloud.anythingmcp.com。 登录、点击 Connectors → Deutsche Bahn Fahrplan、粘贴凭证、生成 MCP API key — 完成。无 Docker、无
git clone、无本地服务器。
Deutsche Bahn Fahrplan + Gemini
Query the Deutsche Bahn (DB) timetable via the community-maintained v6.db.transport.rest proxy over the official HAFAS API. Search stations, look up departures/arrivals in real time, and plan journeys between any two DB stops.
前提条件
完整的设置说明已内置在连接器中 (在 store 中选择连接器时可见)。所需环境变量:
(none — public API)
步骤 1 — 获取凭证
db.transport.rest — a free, no-auth wrapper around Deutsche Bahn's HAFAS endpoints maintained by the public-transport community.
No authentication required, but the service is hosted best-effort — for production use you may want to self-host (see https://github.com/derhuerst/db-rest).
Typical workflow:
- Resolve a station name to a stop
idwithdb_search_locations - Call
db_get_departuresordb_get_arrivalswith that id - For trip planning, use
db_get_journeyswithfromandtostop ids
Time format: All times are ISO 8601 with timezone (e.g. 2026-04-21T08:30+02:00). If omitted, when defaults to now.
…(continued in the in-app connector instructions)
步骤 2 — 安装 adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
步骤 3 — 在 Gemini 中添加连接器
Gemini CLI 从 ~/.gemini/settings.json (Windows: %APPDATA%\gemini\settings.json) 读取 MCP 服务器。添加:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- 从 AnythingMCP 获取你的 MCP API key。
- 保存文件并重启
gemini。 - 在 Gemini CLI 中运行
/mcp—Deutsche Bahn Fahrplan应显示为可用。 - Vertex AI Studio: 将
https://cloud.anythingmcp.com/mcp传入请求的tools数组,使用相同的 Bearer 头。
可用工具
| Tool | What it does |
|---|---|
db_search_locations | Search for DB stops/stations, addresses, or points of interest by name |
db_get_stop | Retrieve details for a specific stop/station by its DB id, including name, location, station category, and products served (ICE, IC, RE, S, |
db_get_departures | List upcoming departures from a stop |
db_get_arrivals | List upcoming arrivals at a stop with origin, planned and actual time, platform, delay, and cancellation status |
db_get_journeys | Plan a journey between two stops |
FAQ
Gemini 1.5 Pro 或 2.x 支持 MCP 吗? 支持 — Gemini CLI ≥ 0.4 与 Vertex AI tools API 均接受带 Bearer 头的 MCP httpUrl 连接器。
下一步
这份指南对你有帮助吗?
