What tools does Exemplo de Servidor MCP provide?
It provides two tools: `get-alerts` (returns active weather alerts for a US state by two-letter code) and `get-forecast` (returns weather forecast for given latitude/longitude).
@renanpk
基本情報
概要はまだありません
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"mcp-server-sample-main": {
"command": "node",
"args": [
"build/main.js"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
Exemplo de Servidor MCP is an educational implementation of a Model Context Protocol server built with Node.js/TypeScript. It provides two weather information tools using the US National Weather Service (NWS) API, and is designed for learning MCP server development.
Clone the repository, run npm install, then npm run build. Execute the server with node build/main.js or link it as a binary via npm link and run weather. The server communicates over stdio and waits for MCP requests.
It provides two tools: `get-alerts` (returns active weather alerts for a US state by two-letter code) and `get-forecast` (returns weather forecast for given latitude/longitude).
Clone the repository, run `npm install`, then `npm run build`. Start the server with `node build/main.js`. Optionally, use `npm link` to run it as the `weather` command.
The server uses Node.js, the `@modelcontextprotocol/sdk` for MCP communication, and Zod for input validation. External API calls are made via the built-in `fetch` function.
It follows a Domain-Driven Design layered architecture with separate folders for domain models, infrastructure services (NWS API calls), application logic (WeatherService), interface controllers (tool registration and validation), and a main entry point.
It communicates over stdio (standard input/output) using the MCP protocol. The server listens for requests on stdin and writes responses to stdout.
Painless E2E Automation for Mobile and Web

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Hindsight: Agent Memory That Learns

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
コメント