Markdownify
Converts various file types and web content, such as PDFs, images, audio, and web pages, into Markdown format.
Markdownify MCP Server

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.
Features
- Convert multiple file types to Markdown:
- 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
-
Clone this repository
-
Install dependencies:
bun installThe
preinstallstep creates a Python virtual environment at.venvand installsmarkitdown[all]. -
Build the project:
bun run build -
Start the server:
bun start
Development
- Use
bun run devto start the TypeScript compiler in watch mode - Modify
src/server.tsto 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:
{
"mcpServers": {
"markdownify": {
"command": "node",
"args": [
"{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
]
}
}
}
Environment variables
All paths default to sensible values; override only when the defaults don't fit your install layout.
| Variable | Default | Purpose |
|---|---|---|
MARKITDOWN_PATH | <project>/.venv/bin/markitdown, then markitdown on PATH | Absolute path to the markitdown executable. Set this when you've installed markitdown system-wide (e.g. pipx install "markitdown[pdf]") instead of using the bundled venv. |
REPOMIX_PATH | <project>/node_modules/.bin/repomix, then repomix on PATH | Absolute path to the repomix executable used by git-repo-to-markdown. |
MD_ALLOWED_PATHS | unset (unrestricted) | Path-delimiter-separated list (: on POSIX, ; on Windows) of directories the server is allowed to read. When set, all file-input tools (pdf-to-markdown, get-markdown-file, etc.) reject paths outside these directories. |
MD_SHARE_DIR | unset | Deprecated alias for MD_ALLOWED_PATHS (single directory). Still honored for backward compatibility. |
Usage with Docker
Build and run:
docker build -t markdownify-mcp .
docker run --rm -i \
-v "$HOME/Documents:/data:ro" \
-e MD_ALLOWED_PATHS=/data \
markdownify-mcp
Notes for the Docker MCP catalog (mcp/markdownify):
- Mount any host directories you want the server to read into the container, then pass the container paths to the tools (e.g.
/data/foo.pdf, not/Users/you/Documents/foo.pdf). - Set
MD_ALLOWED_PATHSto the colon-separated list of mounted directories so the server enforces a read boundary that matches the bind mount. - The published Docker image installs
markitdown[pdf]only — audio transcription and image OCR (audio-to-markdown,image-to-markdown) require the[all]extras and will fail in the slim image. Use the local install (bun install) for the full feature set.
Available Tools
-
youtube-to-markdown: Convert YouTube videos to Markdown -
pdf-to-markdown: Convert PDF files to Markdown -
bing-search-to-markdown: Convert Bing search results to Markdown -
webpage-to-markdown: Convert web pages to Markdown -
image-to-markdown: Convert images to Markdown with metadata -
audio-to-markdown: Convert audio files to Markdown with transcription -
docx-to-markdown: Convert DOCX files to Markdown -
xlsx-to-markdown: Convert XLSX files to Markdown -
pptx-to-markdown: Convert PPTX files to Markdown -
get-markdown-file: Retrieve an existing Markdown file. File extension must end with: *.md, *.markdown.OPTIONAL: set
MD_ALLOWED_PATHSto restrict every file-input tool to a list of directories, e.g.MD_ALLOWED_PATHS=/data/in:/data/out bun start.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
License
This project is licensed under the MIT License - see the LICENSE file for details.
関連サーバー
Kone.vc
スポンサーMonetize your AI agent with contextual product recommendations
Things 3
Manage your tasks and projects in Things 3 on macOS.
Synta
Synta builds, deploys, and self-heals n8n workflows using AI
Todoist
Interact with the Todoist API to manage your tasks using natural language.
Google Services MCP
(MCP) server for Google Workspace. Drive, Gmail, Calendar, Sheets, Docs, Tasks and People via AI agents.
Vivid MCP
Open a business account right from your AI chat
Fibery
Perform queries and entity operations in your Fibery workspace.
protein-mcp-server
Protein structures (PDB, UniProt)
Romanela
Guides any AI agent or AI-assistant to write healthy, maintainable code
Time MCP Server
Provides the current time using IANA timezone names, with automatic system timezone detection.
Gemini Data Analysis & Research
Leverages Google's Gemini AI for data analysis, research paper generation, and automated email delivery.