PDF2MD

Converts PDF files to Markdown format with incremental processing that resumes from existing page markers, supporting both local files and URLs with fallback handling for various content extraction scenarios.

PDF2MD MCP server by Gavin Huang that converts PDF files to Markdown format using AI sampling capabilities through the FastMCP framework. The implementation supports both local file paths and URLs, features incremental conversion that can resume from where it left off by detecting existing page markers, and uses pymupdf4llm for PDF content extraction with fallback handling when AI sampling is unavailable. Built with comprehensive error handling for network issues, file permissions, and invalid formats, it serves developers building document processing workflows, content management systems requiring PDF-to-Markdown conversion, and AI applications that need to extract and format PDF content for further analysis or storage.