MedAdapt Content Server

by ryoureddy

7 158 downloads Not rated yet MIT
GitHub

About

A specialized MCP server for Claude Desktop that enhances AI-assisted medical learning

Details

License
MIT

Explore

- Content Search: Search for medical educational content across multiple sources
- Resource Retrieval: Fetch complete articles, book chapters, and user documents
- Topic Overviews: Generate comprehensive overviews of medical topics
- Learning Resources: Suggest appropriate learning resources based on topic and student level
- Learning Plans: Create structured learning plans with objectives and resources
- Content Analysis: Extract key points, methodologies, and findings from medical resources
- User Content: Import and analyze user-provided documents

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name MedAdapt Content Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository


pip install -r requirements.txt

1. Clone the repository:

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

2. Create a virtual environment (optional but recommended):
bash
python -m venv .venv
source .venv/bin/activate # On Windows, use: .venv\Scripts\activate

3. Install dependencies:
bash
pip install -r requirements.txt

4. Configure (optional):
- Get an NCBI API key for improved rate limits: https://ncbiinsights.ncbi.nlm.nih.gov/2017/11/02/new-api-keys-for-the-e-utilities/
- Create a .env file based on .env.example

bash
python content_server.py
```

search_medical_content

Search for medical content with filters

get_resource_content

Retrieve complete content for a specific resource

get_topic_overview

Generate comprehensive overview of a medical topic

suggest_learning_resources

Get personalized resource recommendations

import_user_document

Upload user-provided learning materials

generate_learning_plan

Create structured learning plan with objectives

extract_article_key_points

Extract key findings from medical articles

The server provides the following tools to Claude:

- search_medical_content: Search for medical content with filters
- get_resource_content: Retrieve complete content for a specific resource
- get_topic_overview: Generate comprehensive overview of a medical topic
- suggest_learning_resources: Get personalized resource recommendations
- import_user_document: Upload user-provided learning materials
- generate_learning_plan: Create structured learning plan with objectives
- extract_article_key_points: Extract key findings from medical articles

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "medadapt content server": {
            "medadapt-content-server": {
                "command": "python",
                "args": [
                    "content_server.py"
                ]
            }
        }
    }
}

McpServers

{
    "medadapt-content-server": {
        "command": "python",
        "args": [
            "content_server.py"
        ]
    }
}

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.

Overview

The MedAdapt Content Server integrates with Claude Desktop to provide tools for searching, retrieving, and analyzing medical education content. It serves as a bridge between Claude and medical knowledge sources, allowing for enhanced AI-assisted learning experiences.

Quick Start

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.