markdownify-mcp

markdownify-mcp

MCP.Pizza Chef: zcaceres

Word documents, spreadsheets, presentations, images, audio recordings, YouTube videos, and web pages all come back as clean readable text your assistant can summarize, quote, or rewrite. Audio is transcribed along the way. No account key is required, but you do need to install it on your own machine first, which takes a few terminal commands, and you can limit which folders it is allowed to read.

Files/PDF
Web/Research
Writing

Use This MCP server To

Turn a PDF into text I can summarize or quote Get a written transcript of a YouTube video Convert a Word file or slide deck into readable text Pull a long web page into clean, plain text Transcribe a recorded meeting or voice memo Read a spreadsheet as text I can ask questions about

README

Markdownify MCP Server

markdownify mcp logo

Markdownify is a Model Context Protocol (MCP) server that converts various file types and web content to Markdown format. It provides a set of tools to transform PDFs, images, audio files, web pages, and more into easily readable and shareable Markdown text.

Markdownify Server MCP server

Features

  • Convert multiple file types to Markdown:
    • PDF
    • Images
    • Audio (with transcription)
    • DOCX
    • XLSX
    • PPTX
  • Convert web content to Markdown:
    • YouTube video transcripts
    • Bing search results
    • General web pages
  • Retrieve existing Markdown files

Getting Started

  1. Clone this repository

  2. Install dependencies:

    bun install
    

    The preinstall step creates a Python virtual environment at .venv and installs markitdown[all].

  3. Build the project:

    bun run build
    
  4. Start the server:

    bun start
    

Development

  • Use bun run dev to start the TypeScript compiler in watch mode
  • Modify src/server.ts to customize server behavior
  • Add or modify tools in src/tools.ts

Usage with Desktop App

To integrate this server with a desktop app, add the following to your app's server configuration:

markdownify-mcp FAQ

Which file types does it handle?
PDF, Word, Excel, PowerPoint, images, and audio files, plus YouTube videos, Bing search results, and ordinary web pages.
Do I need an account or a paid key?
No. It runs on your own computer and nothing in the setup asks for an account.
How hard is setup?
This one wants someone comfortable with a terminal: you clone the project, install it, build it, then point your assistant at the built file.
Can I use this to summarize a long report?
Yes — convert the PDF to text first, then ask your assistant for the summary in the same conversation.
Can I stop it reading files I do not want it touching?
Yes. You can list the only folders it is allowed to open, and anything outside them is refused.
Does audio transcription work in every setup?
Not in the slim container image. Audio and image reading need the full install on your own machine.