AdithDinish/MCP-SERVER-MEDICAL-

Medical MCP Server

A comprehensive Model Context Protocol (MCP) server providing medical drug information and discovery tools.

Overview

This MCP server provides access to a curated database of pharmaceutical information, including drug mechanisms, indications, dosages, side effects, and contraindications. It's designed to assist healthcare professionals, researchers, and developers working with medical data.

Features

Tools Available

1. drug_discovery_data(drug_name: str)

   • Fetch comprehensive information about a specific drug
   • Returns: name, generic name, mechanism, indication, dosage, side effects, contraindications, drug class

2. search_drugs_by_class(drug_class: str)

   • Search for drugs by therapeutic class (e.g., "NSAID", "Statin", "ACE Inhibitor")
   • Returns: list of drugs matching the class with basic information

3. check_drug_interactions(drug1: str, drug2: str)

   • Check for potential interactions between two drugs
   • Returns: severity level, description, and recommendations

4. get_available_drugs()

   • Get a complete list of all drugs available in the database
   • Returns: list of drug names

Resources Available

• file://drug-discovery-db: Complete drug database in structured format

Prompts Available

• drug-info: Template for querying drug information

Current Drug Database

The server currently includes information for:

• Aspirin (NSAID) - Pain relief, anti-inflammatory, antiplatelet therapy
• Metformin (Biguanide) - Type 2 diabetes treatment
• Lisinopril (ACE Inhibitor) - Hypertension and heart failure
• Atorvastatin (Statin) - Cholesterol management
• Amoxicillin (Penicillin antibiotic) - Bacterial infections

Installation

1. Ensure you have Python 3.11+ installed
2. Install dependencies:

   pip install mcp[cli] fastmcp
   

Usage

Running the Server

python main.py

Using with MCP Client

The server can be integrated with any MCP-compatible client. Add the following configuration to your MCP client settings:

{
  "mcpServers": {
    "mcp-server-med": {
      "command": "uv",
      "args": [
        "run",
        "mcp",
        "dev",
        "main.py"
      ]
    }
  }
}

This configuration is also available in the mcp-config.json file for easy copying.

Example Tool Usage

# Get information about aspirin
result = drug_discovery_data("aspirin")

# Search for all NSAID drugs
nsaids = search_drugs_by_class("NSAID")

# Check interaction between aspirin and lisinopril
interaction = check_drug_interactions("aspirin", "lisinopril")

# Get all available drugs
all_drugs = get_available_drugs()

Data Structure

Each drug entry contains:

• name: Brand/common name
• generic_name: Generic pharmaceutical name
• mechanism: How the drug works
• indication: What conditions it treats
• dosage: Typical dosing information
• side_effects: Common adverse effects
• contraindications: When not to use the drug
• drug_class: Therapeutic classification

Important Disclaimers

⚠️ Medical Disclaimer: This tool is for informational purposes only and should not be used as a substitute for professional medical advice, diagnosis, or treatment. Always consult with qualified healthcare professionals for medical decisions.

⚠️ Data Limitations: The current database contains a limited set of drugs for demonstration purposes. In a production environment, this should be connected to comprehensive pharmaceutical databases.

⚠️ Drug Interactions: The interaction checking is simplified and not comprehensive. Always use professional drug interaction databases for clinical decisions.

Development

Adding New Drugs

To add new drugs to the database, extend the drug_db dictionary in main.py with the required fields.

Extending Functionality

The server can be extended with additional tools such as:

• Dosage calculators
• Allergy checking
• Drug scheduling information
• Clinical trial data
• Pharmacokinetic information

License

This project is provided as-is for educational and development purposes.

Contributing

Contributions are welcome! Please ensure any medical information added is from reliable, peer-reviewed sources.