Pandoc

What is mcp-pandoc?

mcp-pandoc is an MCP server that leverages Pandoc to convert documents between various formats. It allows users to transform content while preserving formatting and structure, making it a versatile tool for document management and interoperability. It is officially included in the Model Context Protocol servers open-source project.

How to use mcp-pandoc?

mcp-pandoc can be integrated as an MCP server. Users can configure it via claude_desktop_config.json or install it automatically using Smithery. Once set up, commands like convert-contents can be used to perform conversions. It requires pandoc and uv to be installed, and TeX Live for PDF conversions. Users need to provide complete file paths for output files, especially for advanced formats like PDF and DOCX.

Key Features of mcp-pandoc

• Extensive Format Support: Supports bidirectional conversion for Markdown, HTML, TXT, DOCX, PDF, RST, LaTeX, EPUB, IPYNB, and ODT.
• convert-contents Tool: A primary tool for transforming content with options for input/output formats, file paths, and reference documents for styling.
• Reference Document Styling: Allows using a reference DOCX file for custom styling during DOCX conversions.
• Early Development: Actively being developed with ongoing improvements and expansion of functionality, including PDF support.
• Integration with MCP: Designed as a Model Context Protocol server for broader compatibility and use within MCP ecosystems.

Use Cases of mcp-pandoc

• Document Interoperability: Convert documents between different formats for compatibility across various platforms and applications.
• Content Publishing: Prepare content for publishing in multiple formats (e.g., converting Markdown to PDF or EPUB).
• Automated Workflows: Integrate into automated document processing workflows for batch conversions.
• Academic and Technical Writing: Convert research papers or technical documentation between formats like LaTeX, Markdown, and DOCX.
• Styling and Branding: Apply consistent styling to documents using reference DOCX files for professional outputs.

FAQ about mcp-pandoc

• Q: What formats does mcp-pandoc support? A: It supports Markdown, HTML, TXT, DOCX, PDF, RST, LaTeX, EPUB, IPYNB, and ODT for bidirectional conversion, with PDF being output-only.
• Q: Do I need to install anything to use mcp-pandoc? A: Yes, you need to install pandoc and uv. For PDF conversions, TeX Live is also required.
• Q: Why is my PDF conversion failing? A: A common reason is that xelatex (part of TeX Live) is not found. Ensure TeX Live is properly installed.
• Q: Can I convert from PDF to other formats? A: No, PDF is currently an output-only format. You can convert to PDF, but not from it.
• Q: How do I apply custom styling to my DOCX output? A: You can use the reference_doc parameter in the convert-contents tool, providing the path to a reference DOCX file.
• Q: What if I don't provide a complete file path for output? A: For basic formats, converted content might be displayed in the chat. For advanced formats, it may save to a system temporary directory, but it's best practice to always provide a complete path including filename and extension.

mcp-pandoc: A Document Conversion MCP Server

Officially included in the Model Context Protocol servers open-source project. 🎉

Overview

A Model Context Protocol server for document format conversion using pandoc. This server provides tools to transform content between different document formats while preserving formatting and structure.

Please note that mcp-pandoc is currently in early development. PDF support is under development, and the functionality and available tools are subject to change and expansion as we continue to improve the server.

Credit: This project uses the Pandoc Python package for document conversion, forming the foundation for this project.

📋 Quick Reference

New to mcp-pandoc? Check out 📖 CHEATSHEET.md for

• ⚡ Copy-paste examples for all formats
• 🔄 Bidirectional conversion matrix
• 🎯 Common workflows and pro tips
• 🌟 Reference document styling guide

Perfect for quick lookups and getting started fast!

Demo

🎥 Watch on YouTube

More to come...

Tools

1. convert-contents
   • Transforms content between supported formats
   • Inputs:
     • contents (string): Source content to convert (required if input_file not provided)
     • input_file (string): Complete path to input file (required if contents not provided)
     • input_format (string): Source format of the content (defaults to markdown)
     • output_format (string): Target format (defaults to markdown)
     • output_file (string): Complete path for output file (required for pdf, docx, rst, latex, epub formats)
     • reference_doc (string): Path to a reference document to use for styling (supported for docx output format)
   • Supported input/output formats:
     • markdown
     • html
     • pdf
     • docx
     • rst
     • latex
     • epub
     • txt
     • ipynb
     • odt
   • Note: For advanced formats (pdf, docx, rst, latex, epub), an output_file path is required

📊 Supported Formats & Conversions

Bidirectional Conversion Matrix

From\To	MD	HTML	TXT	DOCX	PDF	RST	LaTeX	EPUB	IPYNB	ODT
Markdown	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
HTML	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
TXT	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
DOCX	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
RST	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
LaTeX	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
EPUB	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
IPYNB	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
ODT	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅

A Note on PDF Support

This tool uses pandoc for conversions, which allows for generating PDF files from the formats listed above. However, converting from a PDF to other formats is not supported. Therefore, PDF should be considered an output-only format.

Format Categories

Category	Formats	Requirements
Basic	MD, HTML, TXT, IPYNB, ODT	None
Advanced	DOCX, PDF, RST, LaTeX, EPUB	Must specify output_file path
Styled	DOCX with reference doc	Custom template support ⭐

Requirements by Format

• PDF (.pdf) - requires TeX Live installation
• DOCX (.docx) - supports custom styling via reference documents
• All others - no additional requirements

Note: For advanced formats:

1. Complete file paths with filename and extension are required
2. PDF conversion requires TeX Live installation (see Critical Requirements section -> For macOS: brew install texlive)
3. When no output path is specified:
   • Basic formats: Displays converted content in the chat
   • Advanced formats: May save in system temp directory (/tmp/ on Unix systems)

Usage & configuration

NOTE: Ensure to complete installing required packages mentioned below under "Critical Requirements".

To use the published one

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

💡 Quick Start: See CHEATSHEET.md for copy-paste examples and common workflows.

⚠️ Important Notes

Critical Requirements

1. Pandoc Installation

• Required: Install pandoc - the core document conversion engine
• Installation:

  # macOS
  brew install pandoc
  
  # Ubuntu/Debian
  sudo apt-get install pandoc
  
  # Windows
  # Download installer from: https://pandoc.org/installing.html
  

• Verify: pandoc --version

2. UV package installation

• Required: Install uv package (includes uvx command)
• Installation:

  # macOS
  brew install uv
  
  # Windows/Linux
  pip install uv
  

• Verify: uvx --version

3. PDF Conversion Prerequisites: Only needed if you need to convert & save pdf

• TeX Live must be installed before attempting PDF conversion
• Installation commands:

  # Ubuntu/Debian
  sudo apt-get install texlive-xetex
  
  # macOS
  brew install texlive
  
  # Windows
  # Install MiKTeX or TeX Live from:
  # https://miktex.org/ or https://tug.org/texlive/
  

4. File Path Requirements

• When saving or converting files, you MUST provide complete file paths including filename and extension
• The tool does not automatically generate filenames or extensions

Examples

✅ Correct Usage:

# Converting content to PDF
"Convert this text to PDF and save as /path/to/document.pdf"

# Converting between file formats
"Convert /path/to/input.md to PDF and save as /path/to/output.pdf"

# Converting to DOCX with a reference document template
"Convert input.md to DOCX using template.docx as reference and save as output.docx"

# Step-by-step reference document workflow
"First create a reference document: pandoc -o custom-reference.docx --print-default-data-file reference.docx" or if you already have one, use that
"Then convert with custom styling: Convert this text to DOCX using /path/to/custom-reference.docx as reference and save as /path/to/styled-output.docx"

❌ Incorrect Usage:

# Missing filename and extension
"Save this as PDF in /documents/"

# Missing complete path
"Convert this to PDF"

# Missing extension
"Save as /documents/story"

Common Issues and Solutions

1. PDF Conversion Fails

   • Error: "xelatex not found"
   • Solution: Install TeX Live first (see installation commands above)

2. File Conversion Fails

   • Error: "Invalid file path"
   • Solution: Provide complete path including filename and extension
   • Example: /path/to/document.pdf instead of just /path/to/

3. Format Conversion Fails

   • Error: "Unsupported format"
   • Solution: Use only supported formats:
     • Basic: txt, html, markdown
     • Advanced: pdf, docx, rst, latex, epub

4. Reference Document Issues

   • Error: "Reference document not found"
   • Solution: Ensure the reference document path exists and is accessible
   • Note: Reference documents only work with DOCX output format
   • How to create: pandoc -o reference.docx --print-default-data-file reference.docx

Quickstart

Install

Option 1: Installing manually via claude_desktop_config.json config file

• On MacOS: open ~/Library/Application\ Support/Claude/claude_desktop_config.json
• On Windows: %APPDATA%/Claude/claude_desktop_config.json

a) Only for local development & contribution to this repo

ℹ️ Replace with your locally cloned project path

"mcpServers": {
  "mcp-pandoc": {
    "command": "uv",
    "args": [
      "--directory",
      "<DIRECTORY>/mcp-pandoc",
      "run",
      "mcp-pandoc"
    ]
  }
}

b) Published Servers Configuration - Consumers should use this config

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

Option 2: To install Published Servers Configuration automatically via Smithery

Run the following bash command to install published mcp-pandoc pypi for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install mcp-pandoc --client claude

• If you face any issue, use the "Published Servers Configuration" above directly instead of this cli.

Note: To use locally configured mcp-pandoc, follow "Development/Unpublished Servers Configuration" step above.

Development

Testing

To run the comprehensive test suite and validate all supported bidirectional conversions, use the following command:

uv run pytest tests/test_conversions.py

This ensures backward compatibility and verifies the tool's core functionality.

Building and Publishing

To prepare the package for distribution:

1. Sync dependencies and update lockfile:

uv sync

2. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /Users/vivekvells/Desktop/code/ai/mcp-pandoc run mcp-pandoc

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

---

Contributing

We welcome contributions to enhance mcp-pandoc! Here's how you can get involved:

1. Report Issues: Found a bug or have a feature request? Open an issue on our GitHub Issues page.
2. Submit Pull Requests: Improve the codebase or add features by creating a pull request.

---