How do I use MedVision MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MedVision MCP Analyze this chest X-ray and describe any clinical findings." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MedVision MCP

Medical Vision AI Tools via Model Context Protocol (MCP)

Overview

MedVision MCP provides AI-powered medical image analysis tools accessible through the Model Context Protocol. It enables LLM agents (like Claude, GitHub Copilot) to analyze X-rays, CT scans, and other medical images.

Features (Roadmap)

🔬 X-ray Analysis: Classification, detection, and findings extraction
🎯 Interactive Segmentation: SAM-based region segmentation
💬 Medical VQA: Visual question answering for medical images
🖼️ Canvas Workspace: Interactive drawing/annotation interface
🤖 Internal Agent: Orchestrates multi-step analysis workflows

Quick Start

# Install pip install medvision-mcp # Run MCP server medvision-mcp

Architecture

┌─────────────────────────────────────────────────────────┐ │ MCP Client (Claude, Copilot) │ └─────────────────────────┬───────────────────────────────┘ │ stdio/SSE ┌─────────────────────────▼───────────────────────────────┐ │ MedVision MCP Server │ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────────┐ │ │ │ Session │ │ Analysis │ │ Canvas │ │ │ │ Tools │ │ Tools │ │ Tools │ │ │ └─────────────┘ └─────────────┘ └─────────────────┘ │ │ │ │ │ ┌───────────────────────▼────────────────────────────┐ │ │ │ Internal Medical Agent │ │ │ │ (Multi-step reasoning & planning) │ │ │ └───────────────────────┬────────────────────────────┘ │ │ │ │ │ ┌───────────────────────▼────────────────────────────┐ │ │ │ Model Registry │ │ │ │ CheXagent │ MAIRA-2 │ LLaVA-Med │ SAM3 │ ... │ │ │ └────────────────────────────────────────────────────┘ │ └─────────────────────────────────────────────────────────┘

Development

# Clone git clone https://github.com/u9401066/medvision-mcp.git cd medvision-mcp # Install dev dependencies pip install -e ".[dev]" # Run tests pytest