Hello World MCP Server
A simple MCP server template demonstrating resources, prompts, and tools with multiple transport options.
README
Hello World MCP Server
A simple TypeScript implementation of a Model Context Protocol (MCP) server with resources, prompts, and tools. This starter project demonstrates MCP fundamentals and serves as a template for building more complex MCP servers.
Features
- Static Resource: Provides a "Hello, World" message when called via
hello://world - Dynamic Resource: Customizable greeting that accepts a name parameter via
greeting://{name} - Prompt: Simple prompt that configures an assistant with "You are a helpful assistant"
- Tool: Echo tool that returns "Hello" plus your input message
- Multiple Transport Options: Run as either a stdio server or HTTP server with Server-Sent Events (SSE)
Installation
npm install
Build
npm run build
Clean
npm run clean
Run
Using STDIO (for integration with Claude Desktop)
npm run start
Using HTTP with SSE (for web clients)
npm run start:http
By default, the HTTP server runs on port 3000. You can change this by setting the PORT environment variable.
Project Structure
.
├── scripts/ # Helper scripts
├── src/ # Source code
│ ├── http.ts # HTTP transport implementation
│ ├── index.ts # Main entry point
│ ├── server.ts # MCP server configuration
│ └── stdio.ts # STDIO transport implementation
├── package.json # Project dependencies and scripts
└── tsconfig.json # TypeScript configuration
Technical Details
- Built with TypeScript and the
@modelcontextprotocol/sdk(v1.7.0+) - Uses Zod for type validation in tools
- HTTP server implemented with Express.js
- Supports Server-Sent Events (SSE) for real-time communication
Using the Server
You can connect to this server using any MCP client, such as Claude Desktop, or build your own client.
Claude Desktop Configuration
To use this server with Claude Desktop, add the following to your claude_desktop_config.json file:
{
"mcpServers": {
"hello-world": {
"command": "node",
"args": ["<path-to-repo>/build/stdio.js"]
}
}
}
HTTP/SSE Client Integration
{
"mcpServers": {
"hello-world": {
"type": "sse",
"url": "http://localhost:3001/sse",
"messageEndpoint": "http://localhost:3001/messages",
"timeout": 30000, // 连接超时时间(毫秒),默认30秒
"reconnect": true, // SSE 断线自动重连
"reconnectInterval": 5000, // 重连间隔(毫秒)
"maxReconnectAttempts": 5 // 最大重连次数
}
}
}
When running in HTTP mode:
- Connect to the SSE endpoint at
/sseto establish a connection - Send messages to the
/messagesendpoint via POST requests - Receive responses through the SSE connection
Replace <path-to-repo> with the absolute path to this repository.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.