mcpField
M
MCP Server

MCP Server

Local
github.comDeveloper Tools3Updated 74w ago

About MCP Server

A TypeScript template for developers building custom MCP servers. It supports stdio and SSE transports and includes example prompts, resources, and tools as a starting point.

Key features

  1. 01stdio and SSE transport support
  2. 02Example prompts, resources, and tools
  3. 03Organized project structure
  4. 04Built with FastMCP

Use cases

  1. 01Starting a new TypeScript MCP server
  2. 02Adding prompts, resources, or tools to a server

MCP support

The template produces servers that expose prompts, resources, and tools to MCP clients over stdio or SSE.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

MCP Server

A TypeScript template repository for creating Model Context Protocol (MCP) servers with support for both stdio (Standard Input/Output) and SSE (Server-Sent Events) transports. This template provides a solid foundation for building MCP servers with a well-organized structure and essential features.

Features

  • 🚀 Built with TypeScript for type safety and better developer experience
  • 🔄 Supports both stdio and SSE transports
  • 📦 Includes example prompts, resources, and tools
  • ⚡ Uses FastMCP for rapid development

Prerequisites

  • Node.js
  • npm or yarn package manager

Getting Started

  1. Create a repo from this template

    Click Use this template > Create a new repository

    screenshot

  2. Clone your repository

    git clone https://github.com/iamtraction/node-mcp-server.git
    cd node-mcp-server
    
  3. Install dependencies

    npm install
    
  4. Start development server

    npm run dev
    

Project Structure

src/
├── prompts/     # MCP prompts
├── resources/   # MCP resources
├── tools/       # MCP tools
└── server.ts    # Main server file

Available Scripts

  • npm run dev - Start development server with hot reload
  • npm run build - Build the TypeScript code
  • npm run start - Start the production server
  • npm run watch - Watch for TypeScript changes
  • npm run lint - Run ESLint to check code quality and style

Adding New Features

Adding a Prompt

Create a new file in src/prompts/ and add it to server.ts. Learn more about MCP Prompts:

import myPrompt from "./prompts/my-prompt.js";
server.addPrompt(myPrompt);
Adding a Resource

Create a new file in src/resources/ and add it to server.ts. Learn more about MCP Resources:

import myResource from "./resources/my-resource.js";
server.addResource(myResource);
Adding a Tool

Create a new file in src/tools/ and add it to server.ts. Learn more about MCP Tools:

import myTool from "./tools/my-tool.js";
server.addTool(myTool);

Configuration

The server can be configured in server.ts. By default, it runs on port 3000 with SSE transport. You can modify the configuration in the server.start() options.:

server.start({
    transportType: "httpStream", // or "stdio"
    httpStream: {
        port: 3000,
    },
});

Learn more about Transports.

Using the MCP Server

stdio Server Setup
{
    "mcpServers": {
        "example-server": {
            "command": "node",
            "args": [ "dist/server.js" ]
         }
    }
}
SSE Server Setup
{
    "mcpServers": {
        "example-server": {
            "url": "https://example-server.com/sse"
         }
    }
}

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Showcase

Have you built something cool with this template? Add it to the showcase!

To add your project to the showcase:

  1. Edit this README.md file
  2. Add your project to the list above using this format:
    - [Your Project Name](link-to-your-project) - Brief description
    
  3. Submit a pull request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Acknowledgments

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.