Markdownify MCP Server

Example Use Cases

• 1

  Ingest and normalize multilingual documents (PDF, DOCX, PPTX, XLSX) into UTF-8-safe Markdown for indexing or LLM consumption.

• 2

  Extract and convert web content or YouTube transcripts into clean Markdown with preserved metadata for downstream processing.

• 3

  Batch-processing of local or remote files into a standardized Markdown output as part of an ETL or content-prep pipeline.

Description

An enhanced fork of the original Markdownify MCP that adds comprehensive UTF-8 encoding support, improved error handling, and performance optimizations. It converts PDFs, Office files, images, audio (with transcription), YouTube transcripts, and web pages into Markdown while preserving metadata and formatting. Designed for batch processing and Windows-compatible UTF-8 handling, it is implemented with Node.js and Python and distributed under the MIT License. Useful for integrating into desktop apps or agent pipelines that need reliable multilingual document conversion.