PreteWorks API

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

One key for the document-to-web pipeline: scrape, AI-extract, build & edit PDFs, fill forms.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "PreteWorks API": {
      "url": "https://api.preteworks.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (29)

• render_html_to_pdf

  Render a full HTML document to a PDF. External subresources are blocked for safety — inline images/fonts as data: URIs. Returns a file_id (for chaining) and a ~1h download URL.

  Parameters:

  • html (required) — string — The complete HTML document to render.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• number_pdf

  Stamp a page number on every page. position: bottom-center (default) | bottom-left | bottom-right | top-center | top-left | top-right. format supports {n} and {total}. Returns a file_id + ~1h URL.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.
  • start — number — First page's number (default 1).
  • format — string — e.g. '{n}' or '{n} / {total}' (default '{n}').
  • position — string — Where to place it (default bottom-center).

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• pdf_info read-only

  Read a PDF's metadata (title, author, subject, keywords, creator, producer, dates) plus page count and page size, as JSON.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• set_pdf_metadata

  Set a PDF's title, author, subject, keywords (array or comma string) and/or creator. Only the fields you provide change. Returns a file_id + ~1h URL.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.
  • title — string
  • author — string
  • creator — string
  • subject — string
  • keywords

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• render_document

  Render a structured document to a PDF from a named template (invoice, receipt, report). Money/totals are computed for you. Returns a file_id (for chaining) and a ~1h download URL.

  Parameters:

  • template (required) — string — Document template.
  • data (required) — object — Template data. invoice/receipt: {seller:{name,address?,email?,logo_url?(data: URI)}, buyer?:{name,address?,email?}, number?, issued?/date?, due?, currency?, items:[{description,qty,unit_price}], tax_rate?, notes?, terms?}; receipt also takes amount_paid?, payment_method?. report: {title, subtitle?, author?, date?, sections:[{heading?,body?}]}. Money is computed server-side.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• merge_pdfs

  Combine 2+ PDFs into a single PDF, in the order given. Inputs are file_ids (from prior tools) or base64 PDFs. Returns a file_id (for chaining) and a ~1h download URL.

  Parameters:

  • pdfs (required) — array — 2+ PDF sources. Each: A file_id from a prior tool result, or a base64-encoded PDF.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• select_pages

  Keep only the specified pages of a PDF (e.g. [1,3,5]) and drop the rest, preserving order. Returns a file_id (for chaining) and a ~1h download URL.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.
  • pages (required) — string — Pages to keep, e.g. '1,3,5-7'.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• rotate_pdf

  Rotate every page of a PDF by 90, 180, or 270 degrees (clockwise). Returns a file_id (for chaining) and a ~1h download URL.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.
  • degrees (required) — number — 90, 180, or 270.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• watermark_pdf

  Stamp a diagonal grey text watermark (e.g. "DRAFT", "CONFIDENTIAL") across every page of a PDF. Returns a file_id (for chaining) and a ~1h download URL.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.
  • text (required) — string — The watermark text.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• extract_pdf_text read-only

  Extract the text content of a PDF — for RAG, summarization, or search. Accepts a file_id (from a prior tool) or a base64-encoded PDF, and returns the text inline. Not OCR: a scanned/image-only PDF returns little or no text.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• images_to_pdf

  Combine PNG/JPEG images (base64) into a PDF, one image per page. Returns a file_id and a ~1h URL.

  Parameters:

  • images (required) — array — Base64-encoded PNG/JPEG images, one per page (max 20).

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• markdown_to_pdf

  Render Markdown to a clean, print-styled PDF. Returns a file_id and a ~1h URL.

  Parameters:

  • markdown (required) — string — The Markdown to render.
  • title — string — Document title.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• split_pdf

  Split a PDF into multiple PDFs — one per page by default, or by page ranges like '1-3;4-6'. Returns a file_id + URL per part.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.
  • ranges — string — e.g. '1-3;4-6'. Omit to split every page.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• read_pdf_form read-only

  List a PDF's form fields (name, type, value, options) as JSON.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• fill_pdf_form

  Fill a PDF's form fields from a map of field -> value; optionally flatten. Returns a file_id and a ~1h URL.

  Parameters:

  • pdf (required) — string — A file_id from a prior tool result, or a base64-encoded PDF.
  • fields (required) — object — Map of field name to value.
  • flatten — boolean — Flatten the form after filling (default false).

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• file_to_markdown read-only

  Convert a Word (.docx), Excel (.xlsx) or CSV file (base64) into clean Markdown — for RAG, agents and pipelines. DOCX keeps headings/lists/tables; spreadsheets become Markdown tables (one per sheet). Returns Markdown inline. Optional 'format' (docx|xlsx|csv) overrides auto-detection.

  Parameters:

  • file (required) — string — Base64-encoded .docx, .xlsx or .csv file.
  • format — string — Optional format hint; auto-detected if omitted.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• data_to_spreadsheet

  Turn rows of data into a downloadable XLSX (default) or CSV. 'rows' is an array of objects (keys → header row) or an array of arrays (first row is the header). Returns a file_id (for chaining) and a ~1h download URL.

  Parameters:

  • rows (required) — array — Array of objects (keys→columns) or array of arrays (first row = header).
  • format — string — Output format (default xlsx).
  • sheet_name — string — Worksheet name (default 'Sheet1').

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• batch_scrape read-only

  Fetch up to 10 public URLs and return each as clean Markdown, in one call — for research/RAG over several pages at once. Private/internal hosts are blocked.

  Parameters:

  • urls (required) — array — 1–10 http/https URLs.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• crawl_site read-only

  Fetch a URL plus up to 7 more same-origin pages it links to (≤8 total), each as clean Markdown. Bounded and synchronous. Private/internal hosts are blocked.

  Parameters:

  • url (required) — string — The root http/https URL.
  • limit — integer — Max pages incl. root (default 5, max 8).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• map_site read-only

  Discover the same-origin URLs linked from a page — the site map, with no page content fetched. Private/internal hosts are blocked.

  Parameters:

  • url (required) — string — The http/https URL to map.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• extract_data read-only

  Extract specified fields from a web page, PDF, or Office file as JSON, using AI. Provide 'fields' plus ONE source: a 'url', a 'pdf' (file_id or base64), or a 'file' (base64 .docx/.xlsx/.csv). Returns a JSON object mapping each field to its value, or null when absent.

  Parameters:

  • fields (required) — array — Field names to extract, e.g. ['invoice total','due date'].
  • pdf — string — A file_id from a prior tool result, or a base64-encoded PDF.
  • url — string — A public http/https URL to read.
  • file — string — A base64-encoded .docx, .xlsx or .csv file (converted to text first).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• summarize_document read-only

  Summarize a web page, PDF, Office file (.docx/.xlsx/.csv), or raw text using AI. Provide ONE source: 'url', 'pdf' (file_id or base64), 'file' (base64), or 'text'. Optional 'max_words'. Returns the summary.

  Parameters:

  • pdf — string — A file_id from a prior tool, or a base64-encoded PDF.
  • url — string — A public http/https URL to read.
  • file — string — A base64-encoded .docx, .xlsx or .csv file.
  • text — string — Raw text to summarize directly.
  • max_words — integer — Approximate target length in words.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• answer_from_document read-only

  Answer a question grounded ONLY in a source document — a web page, PDF, Office file, or raw text. Provide 'question' plus ONE source: 'url', 'pdf', 'file' (base64), or 'text'. Says so when the answer isn't in the document.

  Parameters:

  • question (required) — string — The question to answer from the document.
  • pdf — string — A file_id from a prior tool, or a base64-encoded PDF.
  • url — string — A public http/https URL to read.
  • file — string — A base64-encoded .docx, .xlsx or .csv file.
  • text — string — Raw text to answer from directly.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• docx_to_text read-only

  Extract the text of a .docx document (base64). Returns the text inline.

  Parameters:

  • docx (required) — string — Base64-encoded .docx file.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world no

• docx_to_pdf

  Convert a .docx document (base64) to a PDF. Returns a file_id and a ~1h URL.

  Parameters:

  • docx (required) — string — Base64-encoded .docx file.

  Hints: read-only no · destructive no · idempotent not declared · open-world no

• read_url read-only

  Fetch a public http/https URL and return its main content as clean Markdown — ideal for giving an agent readable web content for research or RAG. Private/internal hosts are blocked.

  Parameters:

  • url (required) — string — The http/https URL to read.

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

• url_to_pdf

  Fetch a public http/https URL and render the live page to a PDF. Returns a file_id (chainable into the PDF tools) and a ~1h download URL. Private/internal hosts are blocked.

  Parameters:

  • url (required) — string — The http/https URL to snapshot.

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• url_to_screenshot

  Fetch a public http/https URL and capture a PNG screenshot. Set full_page for the entire scroll height. Returns a file_id and a ~1h download URL.

  Parameters:

  • url (required) — string — The http/https URL to capture.
  • full_page — boolean — Capture the full scroll height (default: viewport).

  Hints: read-only no · destructive no · idempotent not declared · open-world yes

• scrape_page read-only

  Fetch a public http/https URL and return its rendered HTML, the links on the page, and page metadata (title/description/OpenGraph/canonical/favicon) — in one render. For clean Markdown use read_url instead. Private/internal hosts are blocked.

  Parameters:

  • url (required) — string — The http/https URL to scrape.
  • formats — array — Which representations to return (default: all three).

  Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.