Convert a PDF document to clean Markdown, preserving headings, tables, lists and reading order. Use this whenever an agent needs to read a PDF: reports, papers, invoices, manuals, slide exports. Accepts a public URL or base64 content; no API key needed.

For large PDFs, convert selected pages ('pages': '1,3-5') or page through
the output with 'offset'/'max_chars'. Scanned PDFs are rejected with a
hint to use ocr_document instead.

Convert almost any document to Markdown in one call: DOCX, PPTX, XLSX, EPUB, HTML, CSV/JSON/XML/TXT and PDF are auto-detected from the URL or base64 content. This is the universal 'just give me the text' tool — use it when the file format is unknown or mixed.

Images and scanned PDFs are routed to OCR automatically when the server
has OCR installed. Legacy .doc/.xls/.ppt binaries are not supported.

Extract data tables from a PDF with structure preserved — returns each table's page number, dimensions and content as Markdown, CSV or JSON rows. Ideal for financial statements, spec sheets, price lists and any document where tables matter more than prose. Scans up to 100 pages per call.

Read the plain text of specific PDF pages — the cheapest way to inspect a known location in a large PDF (e.g. after finding page numbers with search_document or get_document_info). Returns text per page without Markdown table reconstruction. 'pages' is required.

Inspect a document before converting it: detected format, page count, title/author metadata, table of contents (PDF), whether the file is scanned (needs OCR) or encrypted. Call this first for unknown or large documents to plan which pages to convert.

Full-text keyword search inside a PDF: returns every match with its page number and a surrounding text snippet. Use it to locate information in large PDFs (manuals, contracts, filings) before reading the exact pages with read_pdf_pages — much cheaper than converting the whole file.

OCR a scanned PDF or image (PNG/JPEG/WebP/BMP/TIFF) and return the recognised text per page. Use this when a PDF has no embedded text layer (convert_pdf_to_markdown will tell you) or when extracting text from screenshots, photos of documents, receipts and forms. Limited to 30 pages per call — narrow with 'pages'.

Split a PDF into multiple PDF documents by page range. Each part comes back with its page count, size and base64 content (parts up to 5 MB), ready to be fed into other doc2md tools or written to a file. Use it to break a large report into chapters, isolate an appendix, or prepare page-limited uploads.

Merge multiple PDFs, in the given order, into a single PDF document. Accepts either public URLs or base64-encoded files (exactly one of the two). Returns the merged file as base64 (up to 10 MB) plus per-input page counts. Useful for re-assembling split reports, combining invoices or building one attachment from several exports.

List and optionally export the images embedded in a PDF — figures, charts, logos and scanned page bitmaps — with page number, pixel dimensions, format and size. Set include_base64=true to get the actual image data (each up to 2 MB) for saving or further processing. Duplicate images are reported once.