Taiwan Garbage Truck Map

dev.yukai由 yukai.dev 发布官方发布者v0.1.0更新于 Oct 25, 2026

台北、新北、台中和高雄的垃圾车停靠与到达时间。

AI 翻译由 AI 模型根据下方的原文描述翻译,可能有误。

原文描述

Garbage truck stops and arrival times for Taipei, New Taipei, Taichung and Kaohsiung.

已验证Streamable HTTP可网页运行

概览

Taiwan Garbage Truck Map 的托管 MCP 服务(mcp.garbage.yukai.dev),由 yukai.dev 发布;无需登录;Streamable HTTP;4 个工具。

暂无 AI 概览:以下信息来自注册中心条目和服务本身。

发布者
yukai.dev
端点
mcp.garbage.yukai.dev
最近检查

安装

在 SourceWeft 中

  1. 打开 控制台中的 Taiwan Garbage Truck Map,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/dev.yukai%2Ftaipei-trash/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "taiwan-garbage-truck-map": {
      "type": "http",
      "url": "https://mcp.garbage.yukai.dev/mcp"
    }
  }
}

README

Taiwan Garbage Truck Map — MCP Server

Read-only Model Context Protocol server for the garbage-truck dataset powering garbage.yukai.dev. Built on mcp-handler 2.x and @modelcontextprotocol/server 2.x, exposing a single stateless Streamable HTTP endpoint supporting MCP protocol versions 2025-11-25, 2025-06-18, and 2025-03-26.

The server reuses the web app's city adapters (../src/cities), keeping field mappings identical across the site and MCP responses. Data is fetched from the published JSON files (DATA_BASE_URL, defaulting to https://garbage.yukai.dev) and cached in memory for one hour per warm instance. Cities load lazily on demand (note: Taichung's dataset is ~50 MB, taking ~1 s on cold load and ~400 MB RSS in memory).

Tools

ToolPurpose
list_citiesList supported cities, their IDs, and geographic bounding boxes
find_nearby_pointsFind stops within 50–2,000 m of a coordinate, sorted nearest first
search_pointsSearch stops in a city by district, village, road, or route keyword
get_scheduleRetrieve a stop along with every stop on its route in arrival order

All tools are annotated read-only and return structuredContent alongside a plain-text summary. All times are in Asia/Taipei.

For New Taipei and Taichung (whose open data includes weekday schedules), each stop includes a weekly schedule (collectionType → ISO weekdays, 1=Mon … 7=Sun) and a servesToday boolean computed in Taiwan time. Taipei and Kaohsiung do not publish weekday schedules, so those fields are omitted. Unlike the web app's default "today only" view for Taichung, the MCP server loads adapters in allDays mode so agents can answer questions about any day of the week.

Development

bash
cd mcpbun installbun test            # query logic + adapter schedule testsbun run typecheckbun dev.ts          # http://localhost:3939/api/mcp

Test interactively with MCP Inspector:

bash
npx @modelcontextprotocol/inspector

Then connect to http://localhost:3939/api/mcp.

Deployment (Vercel)

This directory is deployed as a standalone Vercel project (taipei-trash-mcp), separate from the GitHub Pages web app. The serverless function is bundled with esbuild at build time (bun run build → api/mcp.js) so that extensionless TypeScript imports in ../src/cities resolve cleanly in Node ESM.

To deploy from the repository root (.vercelignore keeps the upload minimal):

  1. Import the repository in Vercel and set Root Directory to mcp.
  2. Leave Include source files outside of the Root Directory enabled (default) so the build can import ../src/cities.
  3. Add the custom domain (vercel api /v10/projects/<id>/domains -X POST -F name=mcp.garbage.yukai.dev) and configure the CNAME and _vercel TXT records at your DNS provider.
  4. Optional environment variables: DATA_BASE_URL, MCP_ALLOWED_ORIGINS (comma-separated allowlist for browser clients).
  5. Rate limiting is enforced via a Vercel Firewall rule (mcp-rate-limit: 60 requests/min per IP on /api/mcp and /mcp).

Production endpoint: https://mcp.garbage.yukai.dev/mcp (also accessible at /api/mcp; fallback https://taipei-trash-mcp.vercel.app). For stdio-only clients, use npx mcp-remote https://mcp.garbage.yukai.dev/mcp.

Discovery Endpoints

  • /mcp/server-card — MCP Server Card (SEP-2127), served as application/mcp-server-card+json from public/server-card.json.
  • /.well-known/ai-catalog.json — AI Catalog entry pointing to the Server Card (also hosted on https://garbage.yukai.dev).
  • /llms.txt — plain-text guide for LLMs.

Directory Listings

  • server.json — the official MCP Registry manifest for this remote-only server. It mirrors public/server-card.json (same name, version, title, description, repository and remote URL) so the two never disagree.

  • Publish it with the official CLI (namespace dev.yukai/* requires DNS or HTTP verification of yukai.dev — GitHub OAuth only grants io.github.*/*):

    bash
    mcp-publisher validate server.jsonmcp-publisher login dns --domain yukai.dev --private-key "$PRIVATE_KEY"mcp-publisher publish server.json
  • Step-by-step submission notes for the official registry, Smithery, Glama, PulseMCP, mcp.so and awesome-remote-mcp-servers (including the copy to paste and the manual account/DNS steps) live in docs/mcp-directory-submission.md.

Security Notes

  • No authentication: all underlying data is public government open data and every tool is strictly read-only.
  • Origin check: requests carrying an Origin header are rejected with 403 unless the origin is listed in MCP_ALLOWED_ORIGINS, per the MCP transport specification. Native and server-side clients do not send an Origin header.

来源:mcp/README.md,提交 d11d646

工具

4

list_cities

List supported cities

List the cities with garbage-truck collection data, with their ids and bounding boxes.

无需输入参数。

find_nearby_points

Find nearby collection points

Find garbage-truck stops near a coordinate in Taipei, New Taipei, Taichung or Kaohsiung, nearest first, with arrival times. Searches every city whose area overlaps the radius unless `city` is given.

输入参数lat必填lng必填citylimitradiusMeters

search_points

Search collection points by name

Search one city's stops by district, village, location or route text (Traditional Chinese). All space-separated terms must match, e.g. "大安區 安和路".

输入参数city必填limitquery必填

get_schedule

Get a stop and its route schedule

Get one collection point by id (from find_nearby_points or search_points) plus every stop on the same route in arrival order.

输入参数pointId必填

版本历史

1
  1. v0.1.0最新Oct 20, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分