Learn MCP By Building

🚀 Model Context Protocol (MCP) Implementation

This project implements the Model Context Protocol (MCP) for building AI tools. It offers a modular framework for creating MCP-compatible servers and clients.

🚀 Quick Start

This project provides a practical implementation of the Model Context Protocol (MCP), which enables seamless interaction between AI assistants and external tools. You can quickly start using it through the following steps:

1. Run the STDIO Server

npm install
node examples/stdio-server.js

2. Run the HTTP/SSE Server

npm install
node examples/http-server.js

3. Create a Custom Tool

1. Create a new file in the src/tools/ directory:

   // src/tools/my-tool.js
   export const myToolDefinition = {
     name: 'my-tool',
     description: 'Describe my tool',
     inputSchema: {
       type: 'object',
       properties: {
         // Define parameters
       },
       required: []
     }
   };
   
   export async function handleMyTool(args) {
     // Implement tool logic
     return {
       content: [
         {
           type: 'text',
           text: 'My tool result'
         }
       ]
     };
   }
   

2. Export the new tool in src/tools/index.js:

   export * from './my-tool.js';
   

✨ Features

🔍 What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open protocol that enables AI assistants to interact with external tools and data sources.

📚 For a detailed overview, please refer to the MCP Notes.

✨ Feature Highlights

📄 License

MIT