What are the prerequisites to run MCP-SERVER-TEMPLATE?
Node.js version 18.x or later, npm, and Git are required.
@vyasa1986
基本信息
暂无概览
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
MCP-SERVER-TEMPLATE is a TypeScript-based starter template for building Model Context Protocol (MCP) servers using the official MCP SDK. It acts as an interface between user queries and tool execution, enabling AI assistants and external systems to dynamically call tools, interpret prompts, and manage resources in a modular and extensible way.
Clone the repository, run npm install, configure environment variables (e.g., TRANSPORT_TYPE, HTTP_PORT) in a .env file, then start the server with npm start (production) or npm run dev (development). Use npm run test:http to test the HTTP transport, npm run mcp:inspector to launch the MCP Inspector GUI for debugging.
Node.js version 18.x or later, npm, and Git are required.
It supports HTTP (stateless, each request creates a new server instance) and stdio (stateful, for persistent communication). The transport is set via the `TRANSPORT_TYPE` environment variable (default: `'stdio'`).
Configuration is done through environment variables in a `.env` file, such as `TRANSPORT_TYPE`, `HTTP_PORT`, `HTTP_HOST`, `SESSION_SUPPORT`, and `LOG_LEVEL`. Defaults are provided for each option.
Run unit tests with `npm test` (Jest). For HTTP transport, start the server with `TRANSPORT_TYPE=http`, then run `npm run test:http` to send a `tools/list` JSON-RPC request and validate the response.
The MCP Inspector is a web-based debugging GUI for visualizing tool calls and server state. Run `npm run mcp:inspector` after building the project to launch it locally (default port 6274).

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

Eased is a library of motion-first React components for shadcn, installed with the shadcn CLI.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo
评论