Doc2md

Acerca de

doc2md acts as a crucial bridge for organizations that have valuable information locked away in binary document formats like PDFs, Word documents, and PowerPoint presentations. By serving as an MCP server, it normalizes these diverse file types into clean Markdown files directly on the filesystem. This makes them immediately ready for ingestion into vector databases, integration with LLM-powered RAG pipelines, or use in knowledge bases, eliminating the need for manual cleanup and ensuring consistent formatting for downstream AI applications.

Características Principales

• Convert DOCX files to Markdown, maintaining formatting, tables, and hyperlinks
• Accepts base64-encoded content for single-file conversions
• Batch convert multiple files at once, with individual error handling
• Convert PDF files to structured Markdown, preserving headings, lists, and tables
• Convert PPTX files to Markdown, with each slide becoming an H2 section including speaker notes
• Auto-detect file type and route to the correct converter based on extension or MIME type
• 1 GitHub stars

Casos de Uso

• Transform a folder of sales decks or reports into Markdown for integration into a knowledge base
• Pipe converted documents directly into a vector database for RAG pipelines
• Utilize with MCP clients like Claude Desktop to convert and then query local documents