Template Nodejs

A TypeScript template for building MCP servers using Streamable HTTP transport.

Overview

This template provides a foundation for creating MCP servers that can communicate with AI assistants and other MCP clients. It includes a simple HTTP server implementation with example tools, resource & prompts to help you get started building your own MCP integrations.

Deploy

Use the following button to clone the repository and directly deploy the server to Alpic

Deploy on Alpic

Prerequisites

• Node.js 22+ (see .nvmrc for exact version)

Installation

1. Clone the repository:

git clone <repository-url>
cd mcp-server-template

2. Install dependencies:

npm install

3. Create environment file:

cp .env.example .env

Usage

Development

Start the development server with hot-reload:

npm run dev

The server will start on http://localhost:3000 and automatically restart when you make changes to the source code.

Production Build

Build the project for production:

npm run build

The compiled JavaScript will be output to the dist/ directory.

Running the Inspector

Use the MCP inspector tool to test your server:

npm run inspector

API Endpoints

• POST /mcp - Main MCP communication endpoint
• GET /mcp - Returns "Method not allowed" (405)
• DELETE /mcp - Returns "Method not allowed" (405)

Development

Adding New Tools

To add a new tool, modify src/server.ts:

server.registerTool(
  "tool-name",
  {
    title: "Tool Title",
    description: "Tool description",
    inputSchema: {
      // Define your parameters using Zod schemas
      param: z.string().describe("Parameter description"),
    },
  },
  async ({ param }): Promise<CallToolResult> => {
    // Your tool implementation
    return {
      content: [
        {
          type: "text",
          text: `Result: ${param}`,
        },
      ],
    };
  },
);

Adding New Prompts

To add a new prompt template, modify src/server.ts:

server.registerPrompt(
  "prompt-name",
  {
    title: "Prompt Title",
    description: "Prompt description",
    argsSchema: {
      // Define your parameters using Zod schemas
      param: z.string().describe("Parameter description"),
    },
  },
  async ({ param }): Promise<GetPromptResult> => {
    return {
      messages: [
        {
          role: "user",
          content: {
            type: "text",
            text: `Your prompt content with ${param}`,
          },
        },
      ],
    };
  },
);

Adding New Resources

To add a new resource, modify src/server.ts:

server.registerResource(
  "resource-name",
  "https://example.com/resource-uri",
  { mimeType: "text/plain" },
  async (): Promise<ReadResourceResult> => {
    return {
      contents: [
        {
          uri: "https://example.com/resource-uri",
          text: "Resource content",
        },
      ],
    };
  },
);

Resources

• Model Context Protocol Documentation
• MCP SDK Documentation
• Express.js Documentation