anupj_github_file_search_mcp_
by anupjGitHub Code Explorer with MCP Integration
Overview
This project demonstrates how to implement the Model Context Protocol (MCP) to create a GitHub code search tool that could be used by AI assistants. The application consists of a Node.js/Express backend that wraps the GitHub API, a browser client that simulates an AI assistant using the API, and MCP-compatible function definitions with JSON Schema.
What is Model Context Protocol?
Model Context Protocol is a standardized way for AI models to interact with external tools and services. It defines:
1. How functions are described to AI models
2. How AI models decide which functions to call
3. How parameters are structured and validated
4. How results are returned in a consistent format
Features
- Search for code across GitHub repositories
- View file contents from repositories
- Search for GitHub repositories
- Function discovery endpoint
- AI assistant simulation interface
Installation
- Clone this repository
- Install dependencies:
shell npm install - Optional: Set up a GitHub API token as the environment variable
GH_TOKENfor higher rate limits
Usage
- Start the server:
shell npm start
or for development with auto-reload:
shell npm run dev - Open your browser and navigate to http://localhost:3000
- Click "Load Available Functions" to see the API capabilities
- Type a query in the input box and press Enter to simulate an AI conversation
API Endpoints
GET /api/mcp/functions- List all available functionsPOST /api/mcp- Call a function with parameters
Implementation Details
The application consists of:
- A Node.js/Express backend that wraps the GitHub API
- A browser client that simulates an AI assistant using the API
- MCP-compatible function definitions with JSON Schema
About
An example to demonstrate how to build and run an MCP server
Resources
Stars
Watchers
Forks
No releases published
No packages published
Invite Gmail Contacts
