GitHub - microsoft/markitdown: Python tool for converting files and office documents to Markdown.
github.com
20 Jan 2025
Started using MarkItDown, a Python utility released by Microsoft for converting various file formats into Markdown.
It's designed to preserve document structure, making it suitable for use with large language models (LLMs) and text analysis pipelines.
Supported formats include:
- PDF, Word, PowerPoint, Excel
- Images (with EXIF metadata and OCR)
- Audio files (with EXIF metadata and speech transcription)
- HTML, CSV, JSON, XML
- ZIP files (iterates over contents)
- YouTube URLs, EPUBs
Installation:
pip install 'markitdown[all]'
Key features:
• Optional dependencies for specific formats
• Plugin support for extensibility
• Integration with Model Context Protocol (MCP) servers for LLM applications like Claude Desktop
MCP
20 Apr 2025
Now MarkItDown offers an MCP (Model Context Protocol) server for integration with LLM applications like Claude Desktop. See markitdown-mcp for more information.
markitdown/packages/markitdown-mcp at main · microsoft/markitdown · GitHub
github.com