Skip to main content
Glama
MD-PDF MCP Server

MD-PDF MCP Server

by kareemaly

MD-PDF MCP Server

A Model Context Protocol (MCP) server for converting between Markdown and PDF formats.

System Requirements

Tested on:

  • macOS 14.3.0 (Darwin 23.3.0, ARM64)

  • Python 3.13.0

  • uv 0.7.13

  • pandoc 3.6.2

Related MCP server: PDF2MD MCP Server

Features

  • Convert Markdown content/files to PDF with size options (small, medium, large)

  • Convert PDF files to Markdown format

  • Extract text from specific PDF pages

  • Retrieve PDF metadata

MCP Tools

  1. convert_markdown_to_pdf(markdown_content, output_filename, size, pdf_engine)

  2. convert_markdown_file_to_pdf(markdown_file_path, output_filename, size, pdf_engine)

  3. convert_pdf_to_markdown(pdf_file_path, output_filename)

  4. extract_text_from_pdf(pdf_file_path, page_numbers)

  5. get_pdf_info(pdf_file_path)

Installation

# Install dependencies
curl -LsSf https://astral.sh/uv/install.sh | sh
brew install pandoc weasyprint

# Setup project
uv sync

Running the Server

uv run python main.py

MCP Integration

Claude Desktop

{
  "mcpServers": {
    "md-pdf": {
      "command": "uv",
      "args": [
        "--directory",
        "/absolute/path/to/md-pdf",
        "run",
        "main.py"
      ]
    }
  }
}

Cursor

Configure MCP in Cursor settings

{
  "servers": {
    "md-pdf": {
      "command": "uv",
      "args": ["run", "main.py"],
      "cwd": "/absolute/path/to/md-pdf"
    }
  }
}

Size Options

  • s: 8pt font, 0.35in margins (compact)

  • m: 9pt font, 0.5in margins (standard)

  • l: 11pt font, 1in margins (detailed)

Project Structure

md-pdf/
├── data/           # Test files
├── tools/          # MCP tool definitions  
├── utils/          # Conversion utilities
├── main.py         # Server entry point
└── server.py       # MCP server instance

Available Tools

5 tools
convert_markdown_file_to_pdfA

Convert a Markdown file to PDF with customizable formatting options.

Args: working_dir: Absolute path to the working directory for file operations markdown_file_path: Path to the markdown file relative to working_dir output_filename: Name of the output PDF file relative to working_dir (if not provided, uses same name as input with .pdf extension) size: Output size - 's' (small/compact), 'm' (medium), 'l' (large/detailed) (default: l) pdf_engine: PDF engine to use - weasyprint or pdflatex (default: weasyprint)

Returns: A message indicating success or failure of the conversion

Inputs: working_dir (required), markdown_file_path (required), output_filename, size, +1 more.

convert_markdown_to_pdfA

Convert Markdown content to PDF with customizable formatting options.

Args: working_dir: Absolute path to the working directory for file operations markdown_content: The markdown content to convert to PDF output_filename: Name of the output PDF file relative to working_dir (default: output.pdf) size: Output size - 's' (small/compact), 'm' (medium), 'l' (large/detailed) (default: l) pdf_engine: PDF engine to use - weasyprint or pdflatex (default: weasyprint)

Returns: A message indicating success or failure of the conversion

Inputs: working_dir (required), markdown_content (required), output_filename, size, +1 more.

convert_pdf_to_markdownB

Convert a PDF file to Markdown format.

Args: pdf_file_path: Path to the PDF file to convert output_filename: Name of the output Markdown file (if not provided, uses same name as input with .md extension)

Returns: A message indicating success or failure of the conversion

Inputs: pdf_file_path (required), output_filename.

extract_text_from_pdfA

Extract text content from a PDF file without conversion to Markdown.

Args: working_dir: Absolute path to the working directory for file operations pdf_file_path: Path to the PDF file relative to working_dir page_numbers: Page numbers to extract - "all" for all pages, or comma-separated numbers like "1,3,5" or "1-5"

Returns: The extracted text content from the PDF

Inputs: working_dir (required), pdf_file_path (required), page_numbers.

get_pdf_infoC

Get information about a PDF file (number of pages, metadata, etc.).

Args: working_dir: Absolute path to the working directory for file operations pdf_file_path: Path to the PDF file relative to working_dir

Returns: Information about the PDF file

Inputs: working_dir (required), pdf_file_path (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 5 tools

    Disambiguation3/5

    There is significant overlap between convert_markdown_file_to_pdf and convert_markdown_to_pdf, which differ only in input type (file vs. content) and could easily be confused. The other three tools have distinct purposes (PDF to Markdown conversion, text extraction, and metadata retrieval), but the two Markdown-to-PDF tools create ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with clear, descriptive actions (convert, extract, get) and objects (markdown_file_to_pdf, pdf_to_markdown, text_from_pdf, pdf_info). The naming is uniform and predictable throughout the set.

    Tool Count5/5

    With 5 tools, this server is well-scoped for its PDF/Markdown conversion domain. The count is appropriate, covering key operations without being overly sparse or bloated, and each tool appears to serve a distinct functional role in the workflow.

    Completeness4/5

    The toolset provides solid coverage for PDF and Markdown interactions, including conversion in both directions, text extraction, and metadata retrieval. A minor gap exists in lacking tools for editing or manipulating PDFs/Markdown files beyond conversion, but core workflows are well-supported.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that converts Markdown text to DOCX format using an external conversion service. It supports custom templates, multi-language output, and provides flexible file handling for both local and cloud-based deployments.
      8
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that provides tools for reading, writing, and manipulating PDF files, including text extraction, metadata retrieval, and merging or splitting documents. It also enables users to create PDFs from plain text and convert specific pages or entire documents into images.
      1
      -