E-Book MCP Server with PDF Conversion

What is E-Book MCP Server with PDF Conversion?

E-Book MCP Server with PDF Conversion is a server that converts HTML files to PDF documents while properly handling embedded images. It is designed for users who need to generate e-books or PDFs from HTML content with robust error handling and automatic temporary file cleanup.

How to use E-Book MCP Server with PDF Conversion?

Install Python 3.9+ and required packages (fastapi, python-docx, pdfkit, reportlab, pydantic, uvicorn, pillow), optionally install wkhtmltopdf. Then use the handle_call_tool function with arguments including text_file, images, and output_pdf as shown in the example with the CREATE_DOC tool name.

Key features of E-Book MCP Server with PDF Conversion

• Convert HTML files to PDF with proper image handling.
• Support for both pdfkit (wkhtmltopdf) and reportlab engines.
• Robust error handling and logging during conversion.
• Automatic temporary file management and cleanup.
• Detailed diagnostic information for conversion processes.

Use cases of E-Book MCP Server with PDF Conversion

• Generate PDF reports from HTML templates with embedded images.
• Create e-books by converting styled HTML content with illustrations.
• Batch convert HTML documents with image assets to PDF format.
• Automate PDF generation in web applications or workflows.

FAQ from E-Book MCP Server with PDF Conversion

What are the runtime requirements?

Python 3.9+ is required. Optional but recommended: wkhtmltopdf for better PDF quality. Python packages include fastapi, pdfkit, reportlab, pydantic, uvicorn, pillow, and python-docx.

How does the server handle image conversion?

The server reads the input HTML, replaces image references with absolute paths, then attempts conversion using pdfkit (if available) or falls back to reportlab.

What happens if wkhtmltopdf is not installed?

The server falls back to reportlab for PDF generation. The fallback is automatic and does not require manual configuration.

Can I use other PDF engines?

Only pdfkit (wkhtmltopdf) and reportlab are supported as documented. No other engines are mentioned.

What data does the server process and where does it live?

The server processes input HTML files and image paths provided in the arguments. There is no mention of persistent data storage; output PDFs are saved to the specified output path.