Extract & OCR

Pull text, tables, images, bookmarks and attachments out of PDFs — the agent-first toolbox.

API · MCPOCR — searchable PDFMake a scanned PDF searchable: pages without a text layer are OCR'd with Tesseract and gain an invisible text layer; pages that already have text are passed through and reported as skipped.On-devicePDF info & metadataPage count, page sizes, metadata, encryption status as JSON.API · MCPExtract imagesPull all embedded images out of a PDF (ZIP, original formats).API · MCPExtract tables (JSON + CSV)Detect tables and return them as tables.json plus one CSV per table (ZIP).On-deviceExtract bookmarks / TOCReturn the document outline as JSON: level, title, target page.On-deviceExtract attachmentsPull all embedded file attachments out of the PDF (ZIP).On-deviceExtract words with bounding boxesPer-word text extraction with exact bounding boxes (points), grouped by page — agent/LLM ready.On-deviceOCR to textOCR a scanned PDF to plain text. Pages that already carry a text layer contribute that text directly (no OCR needed).API · MCPCompare PDFsPage-level diff of two PDFs: which pages are identical, modified (with a unified text diff and similarity score), added or removed. Returns report.json, optionally with rendered diff images highlighting changed pixels.

Keep exploring

All of it is free — see the features tour for how the web tools, MCP server and API fit together, and the pricing page for the (very short) usage policy.