japlete/md-vision-mcp

What it does

japlete/md-vision-mcp is an MCP (Model Context Protocol) server that processes Markdown documents containing inlined images and automatically generates heading indexes. It enables agentic Retrieval-Augmented Generation (RAG) over local documentation or specified URLs, making it ideal for building AI agents that need to understand and retrieve information from markdown-based knowledge bases.

How to set up

This is an MCP server that can be integrated into Claude, ChatGPT, and other compatible platforms. Installation involves cloning the repository from GitHub and configuring it as an MCP server within your AI application. Detailed setup instructions are available on the GitHub repository page. The tool supports multiple platforms including Windows, macOS, and Linux.

Key features

• Processes Markdown files with embedded images for visual context
• Automatically generates and indexes document headings for better navigation
• Enables RAG capabilities for agentic AI systems
• Supports both local documents and allowed remote URLs
• Cross-platform compatibility (Windows, macOS, Linux)
• MCP server protocol for seamless integration with AI tools