MCP-MD-PDF: Markdown to Word/PDF Converter

A simple, reliable Model Context Protocol (MCP) server that converts Markdown files into professional Word (.docx) and PDF documents — with full support for .dotx templates.

MCP-MD-PDF: Markdown to Word/PDF Converter

A simple, reliable Model Context Protocol (MCP) server that converts Markdown files into professional Word (.docx) and PDF documents — with full support for.dotxtemplates.

This tool was born from a practical need. We often write documentation, guides, and technical notes in Markdown — it’s fast, lightweight, and easy to version. But when it’s time to deliver these files to clients or present them professionally, we usually want them to match our project or company style: clean layout, consistent fonts, branded cover page, and polished formatting.

So instead of doing that manually every time, we built a simple flow:

Convert Markdown → Word (.docx using a.dotxtemplate) → PDF

By using Word templates, we could apply our own design once and keep every document consistent. That’s where this small project came from — a quick way to turn Markdown into beautiful, ready-to-share documents that look like they belong to your organization.

- 🚀Fast Conversion– From Markdown to Word or PDF in seconds
- 🎨Template Support– Apply.dotxtemplates for consistent, branded styling
- 📦Batch Processing– Convert multiple files at once
- 🔧Flexible Output– Choose between.docx,.pdf, or both
- 🤖AI-Ready– Built to integrate smoothly with Claude and other MCP-compatible AI tools

Choose the installation method that best fits your needs:

Option 1: Usinguvx(Recommended - No Code Download Needed)

Best for:Claude Desktop users who want the simplest installation.

- Python 3.10+
- For PDF conversion:

- Windows:Microsoft Word (uses COM automation)
- macOS:LibreOffice (brew install --cask libreoffice)
- Linux:LibreOffice (sudo apt-get install libreoffice)

# No code download needed - uvx handles everything uvx mcp-md-pdf

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "md-pdf": { "command": "uvx", "args": ["mcp-md-pdf"] } } }

Restart Claude Desktopfor changes to take effect.

📖 SeeConfiguration sectionfor config file location and alternative setups.

# Install from PyPI (when published) pip install mcp-md-pdf # Or install with development dependencies pip install "mcp-md-pdf[dev]"

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "md-pdf": { "command": "python", "args": ["-m", "md_pdf_mcp.server"] } } }

Restart Claude Desktopfor changes to take effect.

📖 SeeConfiguration sectionfor config file location and alternative setups.

# Step 1: Clone the repository git clone https://github.com/sham-devs/mcp-md-pdf.git cd mcp-md-pdf # Step 2: Install in development mode pip install -e . # Step 3: (Optional) Install dev dependencies pip install -e ".[dev]"

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "md-pdf": { "command": "python", "args": ["-m", "md_pdf_mcp.server"] } } }

Restart Claude Desktopfor changes to take effect.

📖 SeeConfiguration sectionfor config file location and alternative setups.

%APPDATA%\Claude\claude_desktop_config.json

~/Library/Application Support/Claude/claude_desktop_config.json

{ "mcpServers": { "md-pdf": { "command": "uvx", "args": ["mcp-md-pdf"] } } }

{ "mcpServers": { "md-pdf": { "command": "python", "args": ["-m", "md_pdf_mcp.server"] } } }

{ "mcpServers": { "md-pdf": { "command": "python", "args": ["-m", "md_pdf_mcp.server"], "env": { "PYTHONPATH": "/path/to/mcp-md-pdf" } } } }

Close and reopen Claude Desktop for changes to take effect.

After setup, restart Claude Desktop and simply ask:

Convert my README.md to Word format Convert docs.md to PDF using my company-template.dotx Convert all markdown files in the docs folder to both Word and PDF

Convert a single Markdown file to Word or PDF.

- markdown_path(str)– Path to the.mdfile
- output_path(str)– Output base path (no extension)
- output_format(str)–"docx","pdf", or"both"(default:"docx")
- template_path(str, optional)– Path to.dotxtemplate

# Create Word document convert_markdown("README.md", "output", "docx") # Create PDF with template convert_markdown("doc.md", "result", "pdf", "template.dotx") # Create both formats convert_markdown("guide.md", "final", "both", "company.dotx")

Convert multiple Markdown files at once.

- markdown_files(list[str])– List of.mdfiles
- output_dir(str)– Output directory
- output_format(str)–"docx","pdf", or"both"
- template_path(str, optional)– Shared.dotxtemplate

convert_markdown_batch( ["doc1.md", "doc2.md", "doc3.md"], "output", "both", "template.dotx" )

List supported formats and their capabilities.

For detailed feature coverage analysis, seedocs/MARKDOWN_COVERAGE.md

# Install Python COM automation library pip install pywin32

# Method 1: Direct download (easiest) # Visit: https://www.libreoffice.org/download/ # Method 2: Using Chocolatey package manager choco install libreoffice # Method 3: Using winget (Windows Package Manager) winget install TheDocumentFoundation.LibreOffice

# Check if LibreOffice is installed where.exe soffice # Should output: C:\Program Files\LibreOffice\program\soffice.exe

# Method 1: Homebrew (RECOMMENDED - easiest updates) brew install --cask libreoffice # Method 2: Direct download # Visit: https://www.libreoffice.org/download/ # Download LibreOffice_25.x.x_MacOS_aarch64.dmg (M1/M2/M3) # Or LibreOffice_25.x.x_MacOS_x86-64.dmg (Intel Macs)

which soffice # Should output: /Applications/LibreOffice.app/Contents/MacOS/soffice libreoffice --version # Should output: LibreOffice 25.x.x or higher

# Update package list sudo apt-get update # Install LibreOffice (headless mode supported) sudo apt-get install -y libreoffice libreoffice-writer # Optional: Install additional fonts for better compatibility sudo apt-get install -y fonts-liberation fonts-dejavu

# Minimal installation without GUI components sudo apt-get install -y libreoffice-writer libreoffice-calc \ libxinerama1 libfontconfig1 libdbus-glib-1-2 libcairo2 \ libcups2 libglu1-mesa libsm6

sudo dnf install libreoffice libreoffice-writer

libreoffice --version # Should output: LibreOffice 7.x or 25.x # Test headless mode soffice --headless --version # Should output version without GUI

# Clone the repository git clone https://github.com/sham-devs/mcp-md-pdf.git cd mcp-md-pdf # Install with dev dependencies pip install -e ".[dev]" # Run tests pytest # Run tests with coverage pytest --cov=src/md_pdf_mcp --cov-report=html # Format code black src/ tests/ ruff check src/ tests/

- Markdown → Word conversion
- Template application
- MCP server tools
- Unicode, emoji, and edge cases