What do I need to run this template?
You need Node.js, a package manager like `pnpm` (or `npm`), and the ability to run a local build process.
@jatinsandilya
基本情報
Minimal typescript template to build an mcp server
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。
A starter template for building your own Model Context Protocol (MCP) servers. It provides the basic structure and setup needed to create custom MCPs for use with Cursor or Claude Desktop, including TypeScript, a sample tool implementation, and a ready-to-use project structure built with the @modelcontextprotocol/sdk.
Clone the repository, install dependencies with pnpm install, and build the project with pnpm run build. For Cursor, configure it in Settings → MCP with command node ABSOLUTE_PATH_TO_MCP_SERVER/build/index.js. For Claude Desktop, add a JSON entry to its MCP config with the same command and arguments.
@modelcontextprotocol/sdkbuild/ directoryYou need Node.js, a package manager like `pnpm` (or `npm`), and the ability to run a local build process.
Edit `index.ts` and use the `server.tool()` method, providing a name, description, Zod parameters, and an async handler function.
The README does not specify transport or authentication details beyond the basic MCP server setup using the SDK.
No, this is a starter template intended for development and prototyping. You must modify it with your own tool logic before deploying.
The README specifically documents setup for Cursor and Claude Desktop, but the resulting server should be compatible with any MCP host if configured correctly.
Unipile MCP server: LinkedIn MCP (Sales Navigator, Recruiter), WhatsApp, Instagram, Telegram and email MCP for coding agents. Build your LinkedIn, WhatsApp and email API integration from Cursor, Claude Code, Codex.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

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

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
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.
コメント