Doc MCP

🚀 MCP Hospital Assistant

A full - stack intelligent hospital appointment management system powered by React, Node.js, PostgreSQL, and Mistral LLM (via Ollama). It streamlines hospital appointment management with both manual and AI - assisted features.

🚀 Quick Start

🔍 Prerequisites

• Ensure you have PostgreSQL, Node.js, and npm installed on your system.
• You need to have internet access to download Ollama and the Mistral model.

⚙️ Setup Instructions

1. ✅ Install PostgreSQL and create DB

   sudo apt install postgresql postgresql - contrib
   sudo -u postgres psql
   

   Then run the following SQL commands in the psql shell:

   CREATE DATABASE mcp;
   CREATE USER mcpuser WITH PASSWORD 'mcppass';
   GRANT ALL PRIVILEGES ON DATABASE mcp TO mcpuser;
   

2. 📦 Create Schema Connect to the database:

   psql -U mcpuser -d mcp -h localhost
   

   Then create the necessary tables:

   CREATE TABLE doctors (
     doctor_id SERIAL PRIMARY KEY,
     name TEXT,
     department TEXT,
     available_slots JSONB
   );
   
   CREATE TABLE patients (
     patient_id SERIAL PRIMARY KEY,
     name TEXT,
     age INTEGER,
     contact TEXT
   );
   
   CREATE TABLE appointments (
     appointment_id SERIAL PRIMARY KEY,
     doctor_id INTEGER REFERENCES doctors(doctor_id),
     patient_id INTEGER REFERENCES patients(patient_id),
     appointment_time TEXT
   );
   
   CREATE TABLE users (
     id SERIAL PRIMARY KEY,
     username TEXT UNIQUE,
     password TEXT
   );
   
   GRANT ALL PRIVILEGES ON ALL TABLES IN SCHEMA public TO mcpuser;
   GRANT ALL PRIVILEGES ON ALL SEQUENCES IN SCHEMA public TO mcpuser;
   

3. 🧠 Install Ollama with Mistral

   curl -fsSL https://ollama.com/install.sh | sh
   ollama run mistral
   

   Make sure the local Ollama server is running and available on the default port 11434.
4. 🚀 Backend Setup (Node.js)

   cd backend/
   npm install
   node server.js
   

   This starts the backend on: http://localhost:3007
5. 💻 Frontend Setup (React)

   cd frontend/mcp - ui
   npm install
   npm start
   

   This starts the frontend at: http://localhost:3000

✨ Features

🔥 Preview

🎥 Demo Video

▶️ Click here to watch the demo

🏠 Dashboard

💬 LLM Chat Assistant

💬 Manual Booking

🧠 Key Functionalities

✨ Mode 1: Manual via UI

You can click on homepage icons to perform the following actions:

• ➕ Add Doctor
• ➕ Add Patient
• 📅 Book Appointment
• 📋 View Doctors
• 📋 View Appointments

These UI features directly use API endpoints (e.g., /api/execute, /api/book).

🔍 Mode 2: Smart Assistant (LLM - enabled)

From the "Ask Assistant" chat interface, you can type commands such as:

• Show all appointments
• Book appointment for patient John with doctor 2 at 10:00

✅ If MCP Tools is enabled (checkbox at the top), the LLM will:

• 🔎 Understand the user command
• 🔧 Choose the correct tool from tools.json
• 🧠 Generate SQL
• 🔁 Automatically execute API calls behind the scenes

❌ If disabled, the LLM simply gives plain answers (no system change).

🔐 Authentication

• Only authenticated users can access core pages.
• The register page stores hashed credentials securely in PostgreSQL.
• Sessions are stored using express - session.

📚 Documentation

📁 Project Structure

├── backend/
│   ├── server.js              # Node.js + Express backend
│   ├── config/config.js       # PostgreSQL config
│   ├── mcp/                   # All business logic handlers
│   ├── auth/                  # Login, register, session routes
├── frontend/
│   └── mcp - ui/                # React frontend
│       ├── components/        # AddDoctor, Chat, Login, Home etc.
│       └── App.js             # Main route controller

📝 Example Prompts for LLM

• Show all the doctors in doctor table
• Show appointments after 11:00
• Book an appointment with Dr. Renu at 09:00 for John (age 30)

✅ Summary