Gemini MCP Server Chatbot

🚀 MCP Server Using Gemini (GeminiRouter)

This project is an implementation based on the Model Context Protocol (MCP) combined with Google's Gemini Flash 1.5 API, aiming to demonstrate how modular AI services can work together through a centralized router.

🚀 Quick Start

This project is an implementation based on the Model Context Protocol (MCP) and integrated with Google's Gemini Flash 1.5 API. It aims to demonstrate how modular AI services can collaborate through a centralized router.

🧐 What is MCP and How Does It Work Here?

The Model Context Protocol (MCP) is an architectural pattern designed to enable modular and context-aware communication between multiple specialized AI agents or services. This project applies MCP principles to build a scalable and intelligent AI system with dedicated microservices coordinated by a central router.

Each service (or "context") - whether for chatting, web searching, weather information, deep reasoning, or Retrieval Augmented Generation (RAG) - performs a specific function and communicates between the router/client through lightweight requests.

↺ Overview of the Workflow

Here's how the system works from input to output:

1. User Input: The user sends a query from the front-end UI.

2. Routing Logic:

   • The router receives the query and analyzes the intent.
   • Based on keywords, context, or past interactions, the router selects the appropriate server (chat, search, RAG, thinking, etc.) to handle the query.

3. Service Processing:

   • Chat Server: If the query is conversational or informal, it is routed to this server for a quick response.
   • Search Server: For queries that require real-time or factual data (e.g., "What is the capital of Sweden?"), the router calls the Gemini API through this module.
   • RAG Server: For complex questions that require document-based knowledge synthesis, the RAG module uses a retrieval layer + Gemini to generate answers.
   • Thinking Server: For logical reasoning or multi-step problem-solving, the query is sent here for in-depth processing.
   • Weather (via Search): The search server also integrates the OpenWeather API to handle natural language weather queries, such as "What's the weather like in Tokyo?"

4. Response Aggregation:

   • The selected module processes the request and sends it back to the router.
   • The router can optionally combine responses from multiple modules (e.g., a response containing weather and suggestions).

5. Front-end Output: The final response is returned to the user interface and presented in a clean, conversational manner.

✨ Features

• Modular AI Services: Each function (chat, search, RAG, thinking) has a dedicated microservice.
• Centralized Context Router: All services are coordinated through a centralized router.
• Gemini Flash 1.5 Integration: Leverage Google's Gemini technology for powerful AI capabilities.
• OpenWeather Integration: Provide weather information query functionality.

📚 Documentation

Project Architecture

The overall structure of the project is clear and divided into the following main parts:

.
├── src/
│   ├── router/         # Router logic
│   ├── services/      # Various service modules
│   └── components/    # Front-end components
└── package.json       # Project dependencies and scripts

📦 Installation

1. Clone the repository:

git clone https://github.com/your-repository.git
cd GeminiRouter

2. Start the backend:

npm install
npm start

3. Start the front-end:

cd frontend
npm install
npm run dev

🌟 Future Plans

• Integrate the front-end into Docker Compose: Achieve unified management of front-end and back-end services.
• Improve the User Interface (UI): Add more interactive features to enhance the user experience.
• Expand more API integrations: Such as other data sources like weather and news.

🔧 Technical Details

Important Notes

1. The project relies on an Internet connection to access the Gemini and OpenWeather services.
2. Please configure the relevant API keys before use:

# Set in environment variables
export GEMINI_API_KEY=your_key_here
export OPENWEATHER_API_KEY=your_key_here

3. If you need to debug, run:

npm run debug

Through GeminiRouter, we demonstrate the powerful potential of modular AI services in real-world projects. Whether it's chatting, searching, or weather queries, everything is at your fingertips!