japan-transit-mcp

japan-transit-mcp

Enables route planning and transit information retrieval for Japan using the public Transit API. Supports searching stations, planning routes, and checking departures.

Category
访问服务器

README

japan-transit-mcp

Languages: English | 日本語

Japan transit route-search MCP server for the public Transit API at https://api.transit.ls8h.com/.

This is an unofficial client/server wrapper around the public, read-only Transit API. It is not affiliated with, endorsed by, or guaranteed by Transit, transport operators, ODPT, or any other data provider.

Setup

npm install
npm run build

MCP configuration

Use the built stdio server:

{
  "mcpServers": {
    "japan-transit": {
      "command": "node",
      "args": ["/path/to/japan-transit-mcp/dist/index.js"]
    }
  }
}

Replace /path/to/japan-transit-mcp with your local checkout path.

During development you can run:

npm run dev

Tools

  • suggest_places: Search stations, stops, facilities, and addresses. Use the returned endpoint in route planning.
  • suggest_stations: Search station/stop IDs only.
  • reverse_places: Find nearby route-planning endpoints from latitude/longitude.
  • plan_route: Search routes for departure, arrival, first train, or last train.
  • guidance_plan: Search ranked guidance options with strategy and tracking options.
  • get_station: Get station detail, platforms, and serving routes.
  • station_departures: Get a departure board where the source data license permits it.
  • list_feeds: List ingested GTFS/ODPT feeds and attribution.
  • list_operators: List operator branding and license metadata.
  • health: Check API liveness.

Route endpoints can be station IDs such as feedId:stopId or geographic endpoints like geo:35.680960,139.766386.

Example workflow

  1. Call suggest_places with q: "東京駅".
  2. Call suggest_places with q: "新宿駅".
  3. Pass the returned endpoint values to plan_route.

Times returned by the API are seconds from service-date midnight in the result timezone. Values may exceed 86400 for after-midnight service.

Terms, attribution, and reliability

Before publishing or operating this MCP server, review the Transit terms at https://transit.ls8h.com/terms.

  • The Transit API is free, unauthenticated, and read-only, but excessive requests, uses that interfere with service operation, uses that harm third-party rights or terms, and displays that make the service look official are prohibited.
  • Transit data may come from GTFS, ODPT, transport operators, municipalities, OpenStreetMap, GSI, PLATEAU, and other third-party sources. Source licenses and attribution must be respected.
  • Route, timetable, fare, walking, place, map, and source data are not guaranteed to be accurate, complete, current, available, or fit for a particular purpose.
  • Applications that expose API results should make clear that the service is unofficial and that important travel or business decisions should be checked against official operator information.
  • This repository's MIT license covers only this MCP wrapper code. It does not grant rights to Transit API responses, operator marks/logos, timetable data, OpenStreetMap data, ODPT data, or other third-party content.

Use list_feeds and list_operators to retrieve source and license metadata for attribution. Avoid building a bulk timetable redistribution product from API responses, especially for ODPT-derived data.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选