What are the prerequisites?
Node.js 20 or later and npm (or pnpm) are required.
@SamMorrowDrums
基本信息
A minimal Model Context Protocol (MCP) server in TypeScript with hello tool, markdown resource, and prompt. Includes VS Code/devcontainer setup and documentation.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-typescript-starter": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"--",
"npx",
"tsx",
"src/stdio.ts"
]
}
}
}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。
点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。
A feature-complete Model Context Protocol (MCP) server template written in TypeScript. It demonstrates all major MCP features (tools, resources, templates, prompts) with clean, production-ready code. Intended for developers who want to build or learn MCP servers.
Clone the repository, install dependencies with npm install, and build with npm run build. Run the server using npm run start:stdio for local development or npm run start:http for remote deployment. Development mode with live reload is available via npm run dev.
Node.js 20 or later and npm (or pnpm) are required.
Use `npm run dev` to start with `tsx watch` for instant reload on file changes.
It supports stdio transport (`npm run start:stdio`) for local development and HTTP transport (`npm run start:http`) running on port 3000 by default.
Use the MCP Inspector by running `npx @modelcontextprotocol/inspector -- npx tsx src/stdio.ts`. This provides a tools, resources, prompts, and logs tab for full debugging.
The project is licensed under the MIT License.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

The 9apes MCP server lets an AI assistant read the GitHub Actions data 9apes already collects for your organization: runs, jobs, steps, and their durations. Ask it why a build got slower, which jobs take the longest, or

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu
评论