What is MCP Server Template?
MCP Server Template is a lightweight, extensible MCP server implementation built with Express.js and TypeScript, designed for AI‑powered applications that communicate via SSE.
@antoniodevivo
基本情報
A lightweight and extensible MCP (Model Context Protocol) server implementation built with Express.js and TypeScript. This template provides a solid foundation for building AI-powered applications that can communicate with MCP-compatible clients through Server-Sent Events (SSE).
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-template-antoniodevivo": {
"command": "docker",
"args": [
"build",
"-t",
"mcp-template",
"."
]
}
}
}Add a new note to the note store
Update an existing note
Retrieve a specific note
Retrieve all notes from the store
Delete a note from the store
A lightweight and extensible Model Context Protocol (MCP) server implementation built with Express.js and TypeScript. It provides a foundation for building AI-powered applications that communicate with MCP-compatible clients through Server-Sent Events (SSE). The template includes a note management system and is intended for developers starting a new MCP server project.
Clone the repository, run npm install, then npm run build and npm start. The server starts on port 3123 by default. Alternatively, build a Docker image with docker build -t mcp-template . and run docker run -p 3123:3123 mcp-template. To test the SSE endpoint, connect to GET /mcp/sse.
MCP Server Template is a lightweight, extensible MCP server implementation built with Express.js and TypeScript, designed for AI‑powered applications that communicate via SSE.
Node.js 22 or higher and npm are required. Docker is optional for containerized deployment.
The server provides five tools: `add-note`, `update-note`, `get-note`, `get-all-notes`, and `delete-note`. Each accepts parameters such as `noteTitle`, `noteContent`, and `noteTags` (optional) as specified in the README.
All incoming requests are validated at runtime using Zod schemas before processing, ensuring type safety and data integrity.
Environment variables include PORT (default 3123), LOG_LEVEL (default "info"), DOCKER (set to "true" when running in Docker), and DEV (set to "true" for development mode).

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.


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

Manage CI/CD pipelines, debug failed builds, and optimize test suites directly from your AI agents - no terminal required. The CircleCI MCP Server is a remote server hosted by CircleCI that connects AI tools and agents

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