vivekVells/mcp-pandoc

MCP server for document format conversion using pandoc.

What it solves

mcp-pandoc is a Model Context Protocol (MCP) server that allows AI models (like Claude) to convert documents between a wide variety of formats. It solves the problem of AI assistants being unable to natively handle complex document transformations while preserving formatting and structure.

How it works

The server acts as a bridge between an AI agent and the pandoc engine. It provides a convert-contents tool that can take either raw text or a file path as input and transform it into a target format.

Depending on the output format, the tool handles the result differently:

  • Basic formats (Markdown, HTML, TXT, IPYNB) are returned inline to the chat.
  • Advanced formats (PDF, DOCX, ODT, RST, LaTeX, EPUB, PPTX) require a specific output file path to be saved to disk.

Who it’s for

Users of MCP-compatible AI clients who need to automate document conversion, create branded documents using reference templates, or transform technical documentation into various publishing formats.

Highlights

  • Wide Format Support: Supports bidirectional conversion between Markdown, HTML, TXT, DOCX, ODT, RST, LaTeX, EPUB, and IPYNB.
  • Write-Only Outputs: Can generate PDF and PPTX files.
  • Styling Control: Supports reference documents for DOCX, ODT, and PPTX to ensure consistent branding and styling.
  • Advanced Configuration: Allows the use of YAML defaults files for reusable conversion templates and custom Pandoc filters for enhanced processing.

Related

  • Project
    zcaceres/markdownify-mcp

    An MCP server that converts PDFs, images, audio, Office documents, and web content into Markdown format for easier ingestion by AI models.

  • Project
    docling-project/docling-mcp

    A document processing service that uses the Model Context Protocol (MCP) to give AI agents tools for converting PDFs into structured data and generating new documents.

  • Project
    magicrew/doc7

    A document conversion tool that turns PDFs, Office files, and images into AI-ready Markdown using multimodal vision models, supporting local inference for privacy and cost-efficiency.

  • Project
    docling-project/docling

    A document parsing tool that converts complex PDFs, Office files, and multimodal content into structured Markdown or JSON for use in generative AI and RAG pipelines.

  • Project
    chrisryugj/kordoc

    A document processing toolkit for Korean administrative files (HWP, HWPX, PDF, etc.) that converts them to Markdown for AI analysis and generates government-standard documents.