Markdownify

What is Markdownify-mcp?

Markdownify-mcp is a Model Context Protocol (MCP) server designed to convert a wide array of content, including various file types and web content, into Markdown format. It acts as a central hub for transforming diverse information into a standardized, easily readable, and shareable text format.

How to use Markdownify-mcp?

To use Markdownify-mcp, you need to:

1. Clone the repository: Get the project files onto your local machine.
2. Install dependencies: Run pnpm install to set up all necessary packages, including Python dependencies via uv.
3. Build the project: Execute pnpm run build to compile the TypeScript code.
4. Start the server: Use pnpm start to launch the Markdownify-mcp server.

For integration with a desktop application, configure your app's server settings to point to the dist/index.js file and optionally set the UV_PATH environment variable.

Key Features of Markdownify-mcp

Markdownify-mcp offers a comprehensive set of features for content conversion:

• File Type Conversion:
  • PDF to Markdown
  • Images to Markdown (with metadata)
  • Audio to Markdown (with transcription)
  • DOCX to Markdown
  • XLSX to Markdown
  • PPTX to Markdown
• Web Content Conversion:
  • YouTube video transcripts to Markdown
  • Bing search results to Markdown
  • General web pages to Markdown
• Markdown File Retrieval: Ability to retrieve existing Markdown files (with optional directory restriction via MD_SHARE_DIR).

Use Cases of Markdownify-mcp

Markdownify-mcp can be used in various scenarios, including:

• Knowledge Management: Convert diverse documents and web content into a unified Markdown format for easier organization and search.
• Content Archiving: Preserve web pages, videos, and documents in a future-proof Markdown format.
• Data Extraction: Extract text content from PDFs, images, and audio for further analysis or processing.
• AI/ML Context: Provide structured Markdown content to AI models for improved understanding and generation.
• Automated Documentation: Generate Markdown documentation from various sources automatically.

FAQ about Markdownify-mcp

• Q: What is MCP? A: MCP stands for Model Context Protocol, which is a protocol for servers that convert various types of content into a format suitable for AI models.

• Q: Can I contribute to Markdownify-mcp? A: Yes, contributions are welcome. You can submit Pull Requests on the project's GitHub repository.

• Q: Is there support for Windows? A: The project is seeking help from Windows users to add and test Windows support. Interested individuals can post on the designated GitHub issue.

• Q: How can I restrict the directory for retrieving Markdown files? A: You can set the MD_SHARE_DIR environment variable when starting the server to restrict the directory from which files can be retrieved.

Markdownify MCP Server

Help! I need someone with a Windows computer to help me add support for Markdownify-MCP on Windows. PRs exist but I cannot test them. Post here if interested.

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:
  • 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:

   pnpm install
   

Note: this will also install uv and related Python depdencies.

3. Build the project:

   pnpm run build
   

4. Start the server:

   pnpm start
   

Development

• Use pnpm 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:

{
  "mcpServers": {
    "markdownify": {
      "command": "node",
      "args": [
        "{ABSOLUTE PATH TO FILE HERE}/dist/index.js"
      ],
      "env": {
        // By default, the server will use the default install location of `uv`
        "UV_PATH": "/path/to/uv"
      }
    }
  }
}

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_SHARE_DIR env var to restrict the directory from which files can be retrieved, e.g. MD_SHARE_DIR=[SOME_PATH] pnpm run 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.