MCP Gemini Tutorial

🚀 Tutorial on Building Model Context Protocol (MCP) with Gemini

This repository contains the complete code for building a Model Context Protocol (MCP) server using Google's Gemini 2.0 model. For the specific implementation, refer to this article.

🚀 Quick Start

What is the Model Context Protocol (MCP)?

MCP is an open standard developed by Anthropic that allows AI models to seamlessly access external tools and resources. It provides a standardized way for interactions between AI models and tools, eliminating the need for custom integrations for each tool or model.

The main advantages include:

• Interoperability: Any MCP - compatible model can use any compatible tool.
• Modularity: Tools can be easily added or updated without changing the model integration.
• Standardization: A consistent interface reduces integration complexity.
• Separation of Duties: Clearly distinguishes between model functions and tool functions.

Project Overview

This tutorial demonstrates how to:

• Build a complete MCP server integrated with Brave Search.
• Connect it to Google's Gemini 2.0 model.
• Create a flexible architecture for AI - driven applications.

Prerequisites

• Bun (for fast TypeScript execution).
• A Brave Search API key.
• A Google API key to access the Gemini model.

📦 Installation

# Clone the repository
git clone https://github.com/GuiBibeau/mcp-gemini-tutorial.git
cd mcp-tutorial

# Install dependencies
bun install

Environment Setup

Create a .env file and add your API keys:

BRAVE_API_KEY="your_brave_api_key"
GOOGLE_API_KEY="your_google_api_key"

💻 Usage Examples

Basic Usage

bun examples/basic-client.ts

Advanced Usage

bun examples/gemini-tool-function.ts

Project Structure

• src/ - Core implementation and tools of the MCP server.
• examples/ - Example clients demonstrating how to use the MCP server.
• tests/ - Test files for the project.

Implemented Tools

This MCP server mainly implements two tools:

1. Web Search: Performs general internet searches via Brave Search.
2. Local Search: Finds businesses and locations via Brave Search.

Extending the Project

You can add your own tools by following these steps:

1. Define a new tool and provide its schema.
2. Implement the functionality of the tool.
3. Register it with the MCP server.

📚 Documentation

• Official MCP Documentation
• Google Gemini API Documentation
• Brave Search API Documentation

📄 License

MIT

This project was created using bun init with Bun version v1.1.37. Bun is a fast all - in - one JavaScript runtime.