Skip to content

MCP Server Starter Generator

Generate a runnable MCP server project in TypeScript, Python or Go with tools, resources, prompts, stdio or HTTP transport and optional auth.

MCP Server Starter Generator

9 files · 3.9 KB
my-mcp-server/
src/index.ts
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

import { registerTools } from "./tools/index.js";
import { registerResources } from "./resources/index.js";
import { registerPrompts } from "./prompts/index.js";

const server = new McpServer({
  name: "my-mcp-server",
  version: "1.0.0",
});

registerTools(server);
registerResources(server);
registerPrompts(server);

const transport = new StdioServerTransport();
await server.connect(transport);
console.error("my-mcp-server MCP server running on stdio");
Browse existing MCP servers for inspiration?MCP directory →
Need to configure MCP servers in your client?Config generator →

Updated . Provided as is. Check the output before you rely on it in production.

How to use MCP Server Starter Generator

  1. 1

    Choose your language

    Select TypeScript, Python, or Go from the language tabs. Each generates a complete project with the appropriate SDK imports and project structure.

  2. 2

    Configure project settings

    Enter a project name, select your transport method (stdio for local, SSE or Streamable HTTP for remote), and optionally choose an auth method (API Key or OAuth 2.1).

  3. 3

    Define your tools

    Click 'Add Tool' and specify each tool's name, description, and input parameters with types. Use 'Load Sample' for a quick example with realistic tools.

  4. 4

    Add resources (optional)

    Define any static resources or URI templates your server exposes, with MIME types. Resources let AI clients read data from your server.

  5. 5

    Add prompts (optional)

    Define reusable prompt templates with arguments. Prompts help AI clients generate structured requests to your server.

  6. 6

    Preview and download

    Browse the generated file tree, click any file to see its contents. Click 'Download ZIP' to get your complete, ready-to-run MCP server project with README, SDK imports, and Dockerfile.

Questions and answers

What is an MCP server?
A Model Context Protocol server exposes tools, resources and prompts that AI clients such as Claude, Cursor or Windsurf can call over a standard protocol. This generator scaffolds one in TypeScript, Python (FastMCP) or Go (mcp-go) with a stdio, SSE or Streamable HTTP transport, downloadable as a ZIP.
What languages are supported?
TypeScript (using @modelcontextprotocol/sdk), Python (using the mcp package with FastMCP), and Go (using mcp-go). Each generates a complete, ready-to-run project.
What transport methods can I choose?
stdio (for local process-based servers), SSE (Server-Sent Events for remote HTTP), and Streamable HTTP (bidirectional, newest transport). stdio is simplest for getting started.
Is the generated code production-ready?
It's a solid starting point with proper project structure, type definitions, error handling, and a README. You'll need to implement your actual tool logic in the generated handler files.
Does this tool store my data?
No. All code generation happens in your browser. Your tool definitions and generated code never leave your machine. The ZIP is created client-side using JSZip.
For AI agents: how to call this tool

Machine-readable contract, endpoints and examples. Humans can ignore this section.

Best Path For Builders

Browser workflow

Runs instantly in the browser with private local processing and copy/export-ready output.

Browser Workflow

This tool is optimized for instant in-browser execution with local data handling. Run it here and copy/export the output directly.

/mcp-generator/

For automation planning, fetch the canonical contract at /api/tool/mcp-generator.json.