Amount: $50.00
' ``` **Response:** ``` I've generated the PDF from your HTML content. You can access the document here: [URL]. ``` **Prompt:** ``` Convert this Word document to PDF: https://example.com/report.docx ``` **Response:** ``` Processing the conversion... The DOCX file has been successfully converted to PDF. Here is your file: [URL]. ``` **Prompt:** ``` Run OCR on this scanned image to make it searchable: https://example.com/scan.jpg ``` **Response:** ``` I've performed OCR on the image. The text has been extracted and the document is now searchable. You can download it here: [URL]. ``` ## Capabilities ### Create PDFs from web content It takes raw HTML code or structured text and generates a perfectly formatted PDF document. ### Make scanned documents searchable The system runs Optical Character Recognition (OCR) on images or old scans, making all the printed text readable by your agent. ### Convert various file types to PDF You can feed it Office files like DOCX or PPTX, and any image format, and it converts them into standardized PDFs. ### Modify and secure documents The agent lets you apply advanced changes to a PDF, such as redacting sensitive text or adding watermarks across multiple pages. ### Ensure accessibility compliance It automatically tags the structure of PDFs so they meet strict international accessibility standards (PDF/UA). ## Use Cases ### Processing a stack of old forms A compliance officer has 50 scanned patient intake forms. Instead of running each one through an OCR program individually, they ask their agent to run `ocr_document` on the batch and then use `build_document` to merge all the extracted data into a single, searchable PDF record. ### Converting dynamic web content A marketing team needs an invoice based on live HTML data. They prompt their agent with the raw HTML and ask it to run `generate_pdf`, instantly receiving a professionally formatted, printable document without writing any backend code. ### Creating a secure report archive A legal team must send a report that contains confidential client names. They instruct their agent to use `build_document` on the final PDF, applying redaction over all sensitive text before sharing it with non-authorized parties. ### Building a self-service portal document A developer wants to embed user manuals into a client dashboard. They use `convert_to_pdf` on the source files, then ask their agent to create a viewer session using `create_viewer_session`, providing instant, secure access. ## Benefits - Stop dealing with manual OCR steps. The `ocr_document` tool makes scanned or photographic PDFs fully searchable, letting your agent pull out specific data points instantly. - You don't need separate conversion scripts. Use `convert_to_pdf` to handle everything from Word reports (DOCX) to presentation slides (PPTX) and turn them into one consistent PDF format. - Guarantee legal compliance every time. The `autotag_pdf` tool ensures your final PDFs are properly tagged, meeting strict standards for accessibility that reviewers demand. - Handle complex edits in a single step. Instead of multiple passes, use `build_document` to merge reports and redact sensitive information all at once. - Integrate documents into web apps easily. By using `create_viewer_session` and `upload_viewer_document`, you can embed PDFs directly without managing file storage. ## How It Works The bottom line is that your AI client treats complex document formatting as just another conversation topic. 1. First, subscribe to this MCP on Vinkius and enter your unique Nutrient API Key. 2. Next, simply tell your AI client what you need done with the document—for example, 'Generate a PDF from this HTML snippet.' 3. The agent processes the request using its tools and provides you with the finished, compliant file or a link to view it. ## Frequently Asked Questions **How do I convert a Word document to PDF using PSPDFKit (Nutrient)?** You use the `convert_to_pdf` tool. You simply provide your agent with the link or content of the DOCX file, and it handles the conversion process for you. **Can I make a scanned document searchable with PSPDFKit (Nutrient)?** Yes, use `ocr_document`. This tool runs Optical Character Recognition on image or PDF scans, extracting all text so that your agent can search and reference the content. **What is the best way to ensure my PDFs are accessible?** You must run the `autotag_pdf` tool. This ensures the final document includes proper tags, meeting PDF/UA standards required for accessibility compliance. **How do I combine multiple reports and redact data?** The `build_document` tool is what you need. You can ask your agent to merge several files while simultaneously applying redaction or watermarking across the entire set. **Can PSPDFKit (Nutrient) generate a PDF from web code?** Yes, use `generate_pdf`. You feed the raw HTML into your agent, and it outputs a clean, professional-grade PDF file based on that structure.