Medadapt Content Server

🚀 Medical Adaptive Content Server

A professional Model Context Protocol (MCP) server designed for Claude Desktop, which enhances the AI-assisted medical learning experience by fetching and processing content from PubMed, NCBI Bookshelf, and user-provided educational resources.

🚀 Quick Start

# Clone the repository
git clone https://github.com/ryoureddy/medadapt-content-server.git
cd medadapt-content-server

# Install dependencies
pip install -r requirements.txt

# Run the server
python content_server.py

✨ Features

• Content Search: Search for medical educational content across multiple sources.
• Resource Retrieval: Fetch full articles, book chapters, and user-provided documents.
• Topic Overview: Generate comprehensive overviews of medical topics.
• Learning Resource Recommendation: Suggest appropriate educational resources based on topics and student levels.
• Learning Plan Creation: Develop structured learning plans, including goals and resources.
• Content Analysis: Extract key points, methods, and findings from educational content.
• User Content Import: Import and analyze user-provided documents.

📦 Installation

Standard Installation

1. Clone the repository:

git clone https://github.com/ryoureddy/medadapt-content-server.git

2. Navigate to the project directory:

cd medadapt-content-server

3. Install dependencies:

pip install -r requirements.txt

💻 Usage Examples

Configure Claude Desktop

1. Open Claude Desktop.
2. Go to settings and find the MCP server configuration.
3. Fill in the following information:
   • Name: Medical Adaptive Content Server
   • Address: localhost:5000
   • Credentials (Optional): Fill in the corresponding credentials if authentication is required.
4. Save the configuration and enable the MCP server.

Verify the Connection

1. Start the Medical Adaptive Content Server:

python content_server.py

2. In another terminal window, run the following command to test the connection with Claude:

curl -X POST http://localhost:5000/api/test

📚 Documentation

Available Tools

• PubMed API Utility: pubmed_utils.py
• NCBI Bookshelf Utility: bookshelf_utils.py
• Initial Topic Data Population Script: populate_topics.py

Troubleshooting

Common Issues and Solutions

1. Database Path Error

   • Symptom: File or directory not found.
   • Solution: Ensure that the DB_PATH environment variable set in the Claude Desktop configuration is an absolute path and that the application has write permissions.

2. API Rate Limit

   • Symptom: Slow or failed responses from PubMed or NCBI Bookshelf.
   • Solution: Obtain an NCBI API key and add it to the .env file.

3. Claude Desktop Connection Issue

   • Symptom: Claude cannot connect to the MCP server.
   • Solution: Confirm that the server is running and correctly configured in Claude Desktop.

Project Structure

Medical Adaptive Content Server/
│
├── content_server.py     # Main MCP server implementation
├── database.py          # SQLite database interface
├── pubmed_utils.py      # PubMed API utility
├── bookshelf_utils.py   # NCBI Bookshelf utility
├── populate_topics.py   # Script to populate initial topic data
├── test_server.py       # Test script
├── requirements.txt     # Python dependencies
├── .env.example         # Example file for environment variables
└── README.md            # Documentation

📄 License

This project is licensed under the MIT License. For detailed information, please refer to the LICENSE file.

Acknowledgments

• NCBI for providing access to the PubMed and Bookshelf APIs.
• Anthropic for providing Claude and its MCP integration capabilities.