Gemini MCP Server Chatbot

An MCP server implementation based on the Gemini Flash 1.5 API. It coordinates multiple modular AI services (chatting, searching, RAG, deep reasoning, etc.) through a central router to achieve intelligent request distribution and response integration.

Artificial intelligence chatbots Education and learning tools #Modular AI #Intelligent routing #Multi - service collaboration #Gemini integration .JavaScript

rating : 2 points

downloads : 8

update time : 2025-04-29

What is Gemini MCP Router?

This is an intelligent AI service coordination system with a modular design. It can automatically select the most suitable AI service to handle based on the type of user questions. The system includes AI modules with different functions such as chatting, searching, in - depth thinking, and knowledge retrieval, and realizes intelligent assignment through a central router.

How to use Gemini MCP Router?

Just input questions or requests as usual. The system will automatically analyze and select the most suitable service to handle. There is no need to manually select the service type, and the router will make intelligent judgments.

Applicable scenarios

It is suitable for scenarios that require comprehensive AI capabilities, such as daily Q&A, information query, complex problem solving, knowledge retrieval, weather query, etc. It is especially suitable for complex tasks that require multiple AI capabilities to work together.

Main features

Intelligent routingAutomatically analyze user questions and select the most suitable AI service for processing

Multi - service collaborationServices such as chatting, searching, thinking, and knowledge retrieval can work together

Real - time weather queryIntegrate the OpenWeather API to support natural - language weather queries

Deep reasoningA dedicated thinking module handles complex problems that require multi - step reasoning

Knowledge enhancementThe RAG module can combine external knowledge bases to provide more accurate answers

Advantages and limitations

Advantages

Solve multiple AI needs in one stop without switching between different tools

Intelligent routing reduces the user's burden of selection

Modular design allows each service to be independently upgraded

Combines the powerful AI capabilities of Google Gemini with real - time data

Limitations

Requires an internet connection to use

Some complex queries may require a longer response time

Some functions rely on third - party APIs (such as weather data)

How to use

Prepare the environment

Ensure that the Docker and Node.js environments are installed

Configure API keys

Set the API keys for Gemini and OpenWeather in the backend/.env file

Start the backend service

Run the Docker compose command in the backend directory to start all AI microservices

Start the front - end interface

Install dependencies and start the development server in the front - end directory

Start using

Open the front - end interface in the browser and input questions to start using

Usage examples

Daily Q&AHandle general chatting and knowledge - based questions

Real - time information queryGet the latest weather or factual information

Complex problem solvingProblems that require multi - step reasoning or calculation

Knowledge retrieval enhancementQuestions that need to be answered in combination with a specific knowledge base

Frequently Asked Questions

Do I need to pay to use it?

How about the response speed?

Which languages are supported?

How can I know which module handles my question?

Can I add custom modules?

Related resources

GitHub repository

Project source code

Gemini API documentation

Official documentation of Google Gemini

OpenWeather API

Documentation of the weather data API

Docker documentation

Docker usage guide

🚀 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:

User Input: The user sends a query from the front-end UI.
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.
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?"
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).
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

Clone the repository:

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

Start the backend:

npm install
npm start

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

The project relies on an Internet connection to access the Gemini and OpenWeather services.
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

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!