🏥 CareWell Medical Clinic ChatBot

An AI-powered medical clinic chatbot built with Model Context Protocol (MCP) that provides intelligent appointment management and clinic information retrieval through a modern, responsive interface.

✨ Features

• Smart Appointment Management: Book, check, update, and cancel appointments
• Intelligent Information Retrieval: ChromaDB-powered vector search for clinic information
• 24/7 Availability: AI assistant available round the clock
• Mobile-First Design: Fully responsive interface with mobile optimization
• Real-time Chat: Instant responses with typing indicators
• Function Tracking: Visual indicators showing which AI functions were used
• Error Handling: Graceful error handling with user-friendly messages

🚀 Tech Stack

Frontend

• React 19 - Modern UI library
• Vite - Fast build tool and dev server
• TailwindCSS - Utility-first CSS framework
• Lucide React - Beautiful icon library
• Responsive Design - Mobile-first approach

Backend

• Node.js - Runtime environment
• Express.js - Web framework
• MongoDB - Database for appointment storage
• ChromaDB - Vector database for clinic information
• Model Context Protocol (MCP) - AI agent communication protocol

AI & ML

• Google Gemini AI - Large language model
• MCP Server - Tool execution and management
• Vector Search - Semantic information retrieval

📋 Prerequisites

• Node.js (v18 or higher)
• MongoDB (local or cloud instance)
• Google Gemini API key
• npm or yarn package manager

🛠️ Installation & Setup

1. Clone the Repository

git clone https://github.com/sankett13/MCP-Clinic-Bot.git
cd MCP-Clinic-Bot

2. Backend Setup

cd backend
npm install

Create a .env file in the backend directory:

GEMINI_API_KEY=your_gemini_api_key
MONGODB_URI=mongodb://localhost:27017/clinic_chatbot
PORT=5000

3. Frontend Setup

cd frontend/mcp_chatbot
npm install

4. Start the Application

Backend (Terminal 1):

cd backend
npm run dev

Frontend (Terminal 2):

cd frontend/mcp_chatbot
npm run dev

MCP Server Inspector (Terminal 3 - Optional):

cd backend
npm run inspector

The application will be available at:

• Frontend: http://localhost:5173
• Backend API: http://localhost:5000
• MCP Inspector: http://localhost:3000

🏗️ Project Structure

MCP_ChatBot_Clinic/
├── backend/
│   ├── controllers/
│   │   └── chatManager.js
│   ├── models/
│   │   └── appointment.js
│   ├── routes/
│   │   └── mcpRouter.js
│   ├── services/
│   │   ├── initializeChromaDB.js
│   │   ├── initializeMcpServer.js
│   │   └── mcpServer.js
│   ├── chromaDB_store.js
│   ├── connection.js
│   ├── server.js
│   └── package.json
├── frontend/
│   └── mcp_chatbot/
│       ├── src/
│       │   ├── components/
│       │   │   ├── ChatBot.jsx
│       │   │   ├── Header.jsx
│       │   │   ├── Hero.jsx
│       │   │   ├── Services.jsx
│       │   │   ├── About.jsx
│       │   │   ├── Contact.jsx
│       │   │   └── Footer.jsx
│       │   ├── assets/
│       │   ├── App.jsx
│       │   └── main.jsx
│       └── package.json
└── README.md

🔧 Available MCP Tools

The chatbot uses the following MCP tools:

1. createAppointment - Book new appointments
2. checkForAppointments - View existing appointments
3. updateAppointment - Modify appointment details
4. deleteAppointment - Cancel appointments
5. ClinicInfo - Retrieve clinic information using vector search

💬 Usage Examples

Book an Appointment:

User: "I'd like to book an appointment for tomorrow at 2 PM"
Bot: "I'll help you book an appointment. Could you please provide your name, email, and phone number?"

Check Appointments:

User: "Do I have any appointments this week?"
Bot: "Let me check your appointments. What's your name?"

Clinic Information:

User:

... [View full README on GitHub](https://github.com/sankett13/MCP-Clinic-Bot#readme)