Markdownify MCP Server

What does “Markdownify” MCP Server do?

Markdownify MCP Server is a Model Context Protocol (MCP) server designed to convert various file types and web content into Markdown format. It acts as a bridge between AI assistants and external data sources, streamlining the process of transforming documents, images, audio, and web pages into easily readable and shareable Markdown text. By exposing a suite of tools, Markdownify enables tasks such as extracting text from PDFs, retrieving YouTube video transcripts, or converting audio files through transcription. This enhances development workflows by providing standardized, machine-readable content from otherwise complex or unstructured sources, making it easier for AI-powered applications to use, summarize, and process rich information.

List of Prompts

(No prompt templates are explicitly mentioned in the repository or documentation.)

List of Resources

(No explicit MCP resources are detailed in the repository or documentation.)

List of Tools

• youtube-to-markdown: Converts YouTube videos to Markdown by extracting and formatting transcripts.
• pdf-to-markdown: Converts PDF documents into Markdown text.
• bing-search-to-markdown: Converts Bing search results into Markdown summaries.
• webpage-to-markdown: Converts the content of general web pages into Markdown format.
• image-to-markdown: Converts images into Markdown, including metadata.
• audio-to-markdown: Converts audio files into Markdown by transcribing the spoken content.
• docx-to-markdown: Converts Microsoft Word (DOCX) files to Markdown.
• xlsx-to-markdown: Converts Excel (XLSX) files to Markdown tables or text.
• pptx-to-markdown: Converts PowerPoint (PPTX) presentations into Markdown.
• get-markdown-file: Retrieves existing Markdown files (with .md or .markdown extensions) from a specified directory.

Use Cases of this MCP Server

• Document Conversion for Knowledge Management: Easily convert PDFs, DOCX, PPTX, and XLSX files to Markdown for integration into documentation systems, wikis, or knowledge bases, enabling quick search and editing.
• Web Content Summarization: Extract and standardize information from web pages, Bing search results, or YouTube video transcripts for AI-driven analysis, summarization, or reporting.
• Audio and Image Processing: Transcribe podcasts or meeting recordings to Markdown, or convert images for inclusion in Markdown-based repositories, improving accessibility and data reuse.
• Markdown Retrieval and Sharing: Securely retrieve and share existing Markdown documents from a centralized directory, supporting collaborative workflows.
• AI Assistant Contextualization: Allow AI models to access diverse real-world content in a consistent format, improving the quality of responses and actions based on up-to-date, contextual data.

How to set it up

Windsurf

1. Ensure Node.js and pnpm are installed.
2. Clone the repository and install dependencies:

   git clone https://github.com/zcaceres/markdownify-mcp.git
   cd markdownify-mcp
   pnpm install
   

3. Build the project:

   pnpm run build
   

4. Add to Windsurf’s configuration:

   {
     "mcpServers": {
       "markdownify": {
         "command": "node",
         "args": [
           "/absolute/path/to/markdownify-mcp/dist/index.js"
         ],
         "env": {
           "UV_PATH": "/path/to/uv"
         }
       }
     }
   }
   

5. Save configuration and restart Windsurf. Verify the server is running via the app interface.

Securing API Keys Example:

{
  "env": {
    "API_KEY": "${API_KEY}"
  },
  "inputs": {
    "api_key": "${API_KEY}"
  }
}

Claude

1. Install Node.js and pnpm.
2. Clone and install as above.
3. Locate Claude’s MCP server config.
4. Add Markdownify:

   {
     "mcpServers": {
       "markdownify": {
         "command": "node",
         "args": [
           "/absolute/path/to/markdownify-mcp/dist/index.js"
         ],
         "env": {
           "UV_PATH": "/path/to/uv"
         }
       }
     }
   }
   

5. Save, restart Claude, and verify.

Cursor

1. Prerequisite: Node.js, pnpm.
2. Clone and install dependencies.
3. Build with pnpm run build.
4. Edit Cursor’s mcpServers section:

   {
     "mcpServers": {
       "markdownify": {
         "command": "node",
         "args": [
           "/absolute/path/to/markdownify-mcp/dist/index.js"
         ],
         "env": {
           "UV_PATH": "/path/to/uv"
         }
       }
     }
   }
   

5. Save and restart Cursor.

Cline

1. Install Node.js and pnpm, then clone and install as above.
2. Build the project.
3. Add the Markdownify MCP Server to the mcpServers config:

   {
     "mcpServers": {
       "markdownify": {
         "command": "node",
         "args": [
           "/absolute/path/to/markdownify-mcp/dist/index.js"
         ],
         "env": {
           "UV_PATH": "/path/to/uv"
         }
       }
     }
   }
   

4. Save, restart Cline, and verify.

Note: Use environment variables to securely manage API keys (see example above).

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "markdownify": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “markdownify” to the actual name of your MCP server and replace the URL with your own MCP server URL.

Overview

Based on the above tables, Markdownify MCP Server is focused on practical conversion tools and setup guidance, but lacks detail on prompt templates, resources, and advanced MCP features like sampling and roots. The documentation is clear for tools and setup, but information on deeper MCP primitives is missing.

Our opinion

Markdownify MCP Server is robust for document and content conversion use cases, with a wide range of supported file types and good setup documentation. However, the absence of explicit prompt templates, MCP resources, and clarity around advanced features like sampling and roots limits its score for more advanced MCP integrations. For direct practical use in file-to-Markdown conversion, it scores high; for deep protocol extensibility, less so.

MCP Score