🩺 MCP-Based AI Doctor Assistant

Your Virtual Medical Advisor powered by Model Context Protocol (MCP)

⚠️ IMPORTANT DISCLAIMER

This AI assistant is NOT a replacement for professional medical advice, diagnosis, or treatment.

• ❌ Cannot diagnose diseases

• ❌ Cannot prescribe medications

• ❌ Cannot replace a real doctor

• ✅ CAN provide health information

• ✅ CAN detect potential emergencies

• ✅ CAN explain medical terms

Always consult a qualified healthcare provider for medical decisions.

Related MCP server: Epic Patient API MCP Server

🌟 Features

12 Medical Tools

Safety Features

• ✅ Emergency Detection: Automatically detects life-threatening symptoms

• ✅ Medical Disclaimers: Every response includes appropriate warnings

• ✅ No Prescriptions: Never recommends specific medications or dosages

• ✅ Doctor Referral: Always encourages professional consultation

• ✅ Audit Logging: All interactions can be logged for review

🚀 Quick Start

Prerequisites

• Python 3.11 or higher

• pip (Python package manager)

Installation

1. Clone the repository

   git clone <repository-url>
   cd "MCP-Based AI Doctor Assistant"

2. Create virtual environment

   python -m venv venv
   
   # Windows
   .\venv\Scripts\activate
   
   # Mac/Linux
   source venv/bin/activate

3. Install dependencies

   pip install -r requirements.txt

4. Configure environment variables

   # Copy example env file
   cp .env.example .env
   
   # Edit .env and add your Gemini API key (optional, for enhanced AI responses)
   # Get free key at: https://makersuite.google.com/app/apikey

5. Run the server

   python -m src.server

🔧 Configuration

Environment Variables

MCP Configuration

The server can be configured in Claude Desktop or other MCP clients:

{
  "mcpServers": {
    "ai-doctor": {
      "command": "python",
      "args": ["-m", "src.server"],
      "cwd": "/path/to/MCP-Based AI Doctor Assistant"
    }
  }
}

📖 Usage Examples

Checking Symptoms

# Using the MCP tool
{
    "tool": "check_symptoms",
    "arguments": {
        "symptoms": ["headache", "fever", "fatigue"],
        "age": 35,
        "gender": "male",
        "duration": "2 days"
    }
}

Explaining Lab Reports

{
    "tool": "explain_lab_report",
    "arguments": {
        "tests": {
            "hemoglobin": 12.5,
            "wbc": 7500,
            "fasting_glucose": 110
        },
        "gender": "female"
    }
}

Getting Health Advice

{
    "tool": "health_advice",
    "arguments": {
        "topic": "sleep"
    }
}

Emergency Detection

{
    "tool": "detect_emergency",
    "arguments": {
        "symptoms": ["chest pain", "shortness of breath"],
        "context": "Started suddenly while walking"
    }
}

🏗️ Project Structure

MCP-Based AI Doctor Assistant/
├── src/
│   ├── __init__.py
│   ├── server.py           # Main MCP server
│   ├── config.py           # Configuration
│   │
│   ├── core/
│   │   ├── safety_engine.py    # Emergency detection, disclaimers
│   │   ├── llm_client.py       # Gemini API client
│   │   └── memory.py           # Conversation memory
│   │
│   └── tools/
│       ├── symptom_checker.py
│       ├── emergency_detector.py
│       ├── lab_report.py
│       ├── health_advisor.py
│       ├── medicine_info.py
│       ├── mental_health.py
│       ├── diet_nutrition.py
│       ├── first_aid.py
│       ├── pregnancy.py
│       ├── child_health.py
│       ├── chronic_disease.py
│       └── hospital_finder.py
│
├── requirements.txt
├── mcp_config.json
├── .env.example
└── README.md

🔒 Safety & Compliance

Emergency Detection

The system automatically detects critical symptoms like:

• Chest pain / Heart attack signs

• Difficulty breathing

• Signs of stroke (FAST)

• Severe bleeding

• Loss of consciousness

• Suicidal thoughts

• Poisoning

When detected: AI reasoning stops immediately, emergency instructions are provided.

Medical Disclaimers

Every response includes:

• Clear statement that this is not medical advice

• Recommendation to consult healthcare providers

• Emergency contact numbers when appropriate

What This System Does NOT Do

• ❌ Diagnose diseases

• ❌ Prescribe medications

• ❌ Recommend specific dosages

• ❌ Replace professional medical judgment

• ❌ Store personal health information persistently

🌐 Free Deployment Options

Option 1: Render.com

1. Create account at render.com

2. New Web Service → Connect GitHub

3. Add environment variables

4. Deploy (Free tier: 750 hours/month)

Option 2: Railway.app

1. Create account at railway.app

2. New Project → Deploy from GitHub

3. Add environment variables

4. Deploy (Free tier: $5 credit/month)

🧪 Testing

# Run tests
pytest tests/ -v

# Run with coverage
pytest tests/ --cov=src --cov-report=html

📞 Emergency Contact Numbers

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repository

2. Create a feature branch

3. Make your changes

4. Submit a pull request

Guidelines

• Always maintain safety features

• Add appropriate disclaimers

• Test emergency detection

• Document new features

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• Built using Model Context Protocol (MCP)

• Medical information sourced from WHO, CDC, NIH public guidelines

• Emergency protocols based on standard first aid guidelines

⚠️ Final Reminder

This AI assistant provides INFORMATION, not MEDICAL ADVICE.

For any health concerns:

1. 🏥 Consult a qualified healthcare provider

2. 📞 Call emergency services for urgent situations

3. 🚑 Visit the nearest hospital for serious symptoms

Your health matters. Trust professionals, not AI.

Made with ❤️ for better health awareness