Github File Search MCP

🚀 GitHub Code Browser Implemented with Model Context Protocol

This project demonstrates how to use the Model Context Protocol (MCP) to create a GitHub code search tool that can be used by AI assistants.

🚀 Quick Start

This project showcases a GitHub code search tool built with MCP for AI assistants. To get started:

1. Launch the server:

   npm start
   

   Or use auto - reload in the development environment:

   npm run dev
   

2. Open your browser and navigate to http://localhost:3000.
3. Click "Load available functions" to view API features.
4. Enter a query in the input box and press Enter to simulate an AI conversation.

✨ Features

• Search for code in GitHub repositories.
• View the content of files in repositories.
• Search for GitHub repositories.
• Function discovery endpoint.
• AI assistant simulation interface.

📦 Installation

1. Clone this repository.
2. Install dependencies:

   npm install
   

3. Optionally, set the GitHub API token as an environment variable GH_TOKEN to increase the rate limit.

💻 Usage Examples

Basic Usage

To start the server in a production environment:

npm start

Advanced Usage

To start the server with auto - reload in a development environment:

npm run dev

📚 Documentation

What is the Model Context Protocol?

The Model Context Protocol is a standardized approach for defining how AI models interact with external tools and services. It includes the following aspects:

1. How to describe functions to an AI model.
2. How to let an AI model decide which functions to call.
3. How to structure and validate parameters.
4. How to return results in a consistent format.

API Endpoints

• GET /api/mcp/functions - List all available functions.
• POST /api/mcp - Call a function with parameters.