MCP Server PDF Conversion

🚀 E-Book MCP Server with PDF Conversion Function

A server project for creating e-books and PDF files from HTML content with embedded images. This project offers a powerful function to convert HTML files to PDFs while properly handling embedded images.

🚀 Quick Start

This server project is designed to create e-books and PDF files from HTML content with embedded images. It provides a robust solution for converting HTML to PDF while handling images correctly.

✨ Features

• Convert HTML files to PDF documents and handle embedded images correctly.
• Support two PDF generation engines: pdfkit (wkhtmltopdf) and reportlab.
• Robust error handling and logging functionality.
• Automatically manage temporary files with a cleanup mechanism.
• Provide detailed diagnostic information during the conversion process.

📦 Installation

Prerequisites

• Python 3.9+
• wkhtmltopdf (optional but recommended for better PDF quality)
• Python dependencies:
  • fastapi
  • python-docx
  • pdfkit
  • reportlab
  • pydantic
  • uvicorn
  • pillow

Steps

1. Clone this repository.
2. Install the required Python packages:

   pip install fastapi python-docx pdfkit reportlab pydantic uvicorn pillow
   

3. Install wkhtmltopdf (optional):
   • Windows: Download and install from wkhtmltopdf.org.
   • Linux: sudo apt-get install wkhtmltopdf
   • macOS: brew install wkhtmltopdf

💻 Usage Examples

Basic Usage

The server provides a function named handle_call_tool that accepts the following parameters:

arguments = {
  "text_file": "input/path/to/input.html",
  "images": {
    "image1.png": "path/to/image1.png",
    "image2.jpg": "path/to/image2.jpg"
  },
  "output_pdf": "output/path/to/output.pdf"
}

Advanced Usage

result = await handle_call_tool("CREATE_DOC", {
    "text_file": "document.html",
    "images": {
        "header.png": "images/header.png",
        "footer.jpg": "images/footer.jpg"
    },
    "output_pdf": "output/document.pdf"
})

📚 Documentation

How It Works

1. The server processes the input HTML file.
2. Replaces image references in the HTML with absolute paths.
3. Tries to convert the HTML to PDF using pdfkit (if available).
4. Falls back to using reportlab if pdfkit fails or is unavailable.
5. Saves the generated PDF to the specified output path.

Project Structure

• main.py: Contains the core functionality for PDF conversion.
• pyproject.toml: Project metadata and dependencies.