概览
What is MedAdapt Content Server?
A specialized Model Context Protocol (MCP) server for Claude Desktop that enhances AI-assisted medical learning by fetching and processing educational resources from PubMed, NCBI Bookshelf, and user-provided documents.
How to use MedAdapt Content Server?
Clone the repository, install Python dependencies with pip install -r requirements.txt, and run python content_server.py. Integrate with Claude Desktop by adding a server entry in claude_desktop_config.json pointing to the script and setting the DB_PATH environment variable. Optionally populate initial topic mappings with python populate_topics.py.
Key features of MedAdapt Content Server
- Search medical content across multiple sources with filters
- Retrieve complete articles, book chapters, and user documents
- Generate comprehensive topic overviews and learning plans
- Provide personalized learning resource recommendations
- Import and analyze user-provided learning materials
- Extract key points and findings from medical articles
Use cases of MedAdapt Content Server
- Medical student asking Claude for a big‑picture overview of the cardiac cycle
- Clinician seeking recent research articles about COVID‑19 treatment options
- Second‑year medical student receiving a structured learning plan for stroke pathophysiology
FAQ from MedAdapt Content Server
What runtime dependencies does it require?
Python installed along with the packages listed in requirements.txt. A virtual environment is optional but recommended.
How can I handle API rate limiting when searching PubMed or NCBI Bookshelf?
Obtain an NCBI API key from NCBI’s website and add it to your .env file. This improves rate limits and prevents slow or failed responses.
How do I configure the database path correctly?
Set the DB_PATH environment variable in your Claude Desktop configuration to an absolute path (e.g., /absolute/path/to/medadapt-content-server/medadapt_content.db). This prevents sqlite3.OperationalError file access issues.
Can I import my own documents for analysis?
Yes, the server provides the import_user_document tool to upload and analyze user-provided medical learning materials.
Is there any authentication or access control for the server?
No authentication is built in. The server is intended for local use with Claude Desktop; the optional NCBI API key enhances PubMed/Bookshelf access rates but is not required.
