What transport methods does MCP Template support?
It supports two transports: stdio (local, command‑line mode) and SSE over HTTP (can run locally or remotely and be shared across machines).
@davini-dev
基本情報
MCP Server Template
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": {
"my-mcp-stdio": {
"command": "npm",
"args": [
"start"
],
"env": {
"NODE_ENV": "development"
}
},
"my-mcp-sse": {
"url": "http://localhost:3001/sse"
}
}
}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。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
MCP Template is a CLI tool that generates a starter project for building MCP (Model Context Protocol) servers using the FastMCP framework. It provides a preconfigured TypeScript project with dual transport support (stdio and HTTP), sample definitions for tools, resources, and prompts, and development scripts. It is intended for developers who want to quickly create their own MCP servers.
Run npx @mcpdotdirect/create-mcp-server or npm init @mcpdotdirect/mcp-server to scaffold a new project. Then install dependencies with your preferred package manager and start the server using npm start (stdio mode) or npm run start:http (HTTP mode). Development modes with auto‑reload are available via npm run dev and npm run dev:http.
It supports two transports: stdio (local, command‑line mode) and SSE over HTTP (can run locally or remotely and be shared across machines).
In Cursor go to Settings > Features > MCP Servers, add a new server. For stdio, choose type `command` and enter `npm start`. For SSE, choose type `url` and enter `http://localhost:3001/sse`.
Set the `PORT` environment variable before starting the HTTP server, for example: `PORT=8080 npm run start:http`.
Use FastMCP’s built‑in tools: `npx fastmcp dev server.js` or `npx fastmcp inspect server.ts`.
Yes. The default scripts use Bun, but you can modify the `package.json` scripts to use Node.js or another runtime of your choice.
JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app

Design review for UI code, inside your agent. quick_review checks the files you just changed in about ten seconds. review_files returns a 0-100 score and patches. verify_fixes confirms the fixes landed, free. review_url

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.
コメント