Cafeteria MCP
Configurable MCP server for cafeteria menu lookup.
README
Cafeteria MCP
Configurable MCP server for cafeteria menu lookup.
The server exposes a single MCP tool, get_cafeteria_menu, and supports stdio plus HTTP/SSE transports.
Configuration
Set these environment variables in your runtime or hosting provider:
CAFETERIA_API_URL=<form-post-api-url>
CAFETERIA_CAMPUS=<campus-code>
CAFETERIA_SEQ=<cafeteria-sequence>
CAFETERIA_ORIGIN=<optional-origin-header>
CAFETERIA_SKIP_TLS_VERIFY=false
MCP_TRANSPORT=http
CAFETERIA_ORIGIN is optional. When omitted, the origin is derived from CAFETERIA_API_URL.
The upstream request is sent as POST with query parameters and Content-Length: 0.
Set CAFETERIA_SKIP_TLS_VERIFY=true only when the upstream cafeteria API requires curl-style -k behavior.
Tool
get_cafeteria_menu
ymd: lookup date,YYYYMMDDorYYYY-MM-DD. Defaults to today in Asia/Seoul.mealType:LNfor lunch,DNfor dinner.
Local stdio
npm start
MCP client example:
{
"mcpServers": {
"cafeteria": {
"command": "node",
"args": [
"/absolute/path/to/src/server.mjs"
]
}
}
}
HTTP/SSE
MCP_TRANSPORT=http PORT=3333 npm start
- Health check:
GET http://127.0.0.1:3333/health - MCP SSE:
GET http://127.0.0.1:3333/sse - MCP SSE message post:
POST http://127.0.0.1:3333/messages?sessionId=... - MCP JSON-RPC test endpoint:
POST http://127.0.0.1:3333/mcp
Hosting environments that provide PORT automatically run the HTTP/SSE transport.
Render
Deploy the repository with the included render.yaml Blueprint.
After deployment, set the required secret environment variables in Render. The public MCP SSE URL will be:
https://<render-service-name>.onrender.com/sse
See outputs/render-sse-mcp.md for a short registration note.
Supabase Probe
This repository also includes a Supabase Edge Function probe at supabase/functions/cafeteria-probe.
Use it before porting the MCP server to confirm whether the Supabase runtime can reach the cafeteria API.
Required Supabase secrets:
CAFETERIA_API_URL
CAFETERIA_CAMPUS
CAFETERIA_SEQ
CAFETERIA_ORIGIN
Probe URLs after deployment:
https://<project-ref>.functions.supabase.co/cafeteria-probe?target=google
https://<project-ref>.functions.supabase.co/cafeteria-probe?target=cafeteria&ymd=20260608&mealType=LN
Supabase MCP
The Supabase Edge Function MCP endpoint is available at:
https://<project-ref>.functions.supabase.co/cafeteria-mcp
It supports MCP JSON-RPC methods including initialize, tools/list, and tools/call.
Tests
npm run test:sse
npm run test:mcp
npm run test:api -- 20260608 LN
test:api requires the environment variables above.
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。