Use it from an AI agent.
The whole API is also an MCP server. Add it once and your agent can turn web pages into Markdown, structured data, PDFs or screenshots, and create, edit and read PDFs — templates, forms, text extraction and more — 29 tools, same key, same prices.
Install
Claude Code
claude mcp add --transport http preteworks \ https://api.preteworks.com/mcp \ --header "Authorization: Bearer YOUR_API_KEY"
Claude Desktop, Cursor, any MCP client
Transport is Streamable HTTP. Add this server entry to your client's MCP config:
{
"mcpServers": {
"preteworks": {
"url": "https://api.preteworks.com/mcp",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}
}
}
No key yet? Get one on the free tier — 500 units a month, no card, MCP included.
Tools
29 tools
| Tool | Does | Price | HTTP twin |
|---|---|---|---|
| render_html_to_pdf | Render HTML to PDF — Render an HTML document to a pixel-accurate PDF. | $0.01 | /v1/pdf/html |
| merge_pdfs | Merge PDFs — Combine two or more PDFs into one, in order. | $0.002 | /v1/pdf/merge |
| select_pages | Select PDF pages — Keep exactly the pages you want. | $0.002 | /v1/pdf/select |
| rotate_pdf | Rotate PDF — Rotate every page by 90, 180 or 270 degrees. | $0.002 | /v1/pdf/rotate |
| watermark_pdf | Watermark PDF — Stamp a diagonal text watermark across every page. | $0.002 | /v1/pdf/watermark |
| extract_pdf_text | Extract text from a PDF — Pull clean text (and metadata) out of a PDF — for RAG, search and agents. | $0.002 | /v1/pdf/extract |
| markdown_to_pdf | Render Markdown to PDF — Render Markdown to a clean, print-styled PDF — for reports and agent output. | $0.01 | /v1/pdf/from-markdown |
| images_to_pdf | Images to PDF — Combine PNG/JPEG images into a PDF, one image per page. | $0.002 | /v1/pdf/from-images |
| split_pdf | Split a PDF — Split one PDF into many — one file per page, or by page ranges. | $0.002 | /v1/pdf/split |
| read_pdf_form | Read a PDF form — List a PDF's form fields — names, types, values and options. | $0.002 | /v1/pdf/form-read |
| fill_pdf_form | Fill a PDF form — Fill a PDF's form fields from a JSON map; optionally flatten. | $0.002 | /v1/pdf/form-fill |
| number_pdf | Number PDF pages — Stamp page numbers on every page — position, start value and format are yours. | $0.002 | /v1/pdf/number |
| pdf_info | Read PDF info — Read a PDF's metadata and structure — title, author, page count and size. | $0.002 | /v1/pdf/info |
| set_pdf_metadata | Set PDF metadata — Set a PDF's title, author, subject, keywords or creator. | $0.002 | /v1/pdf/metadata |
| docx_to_text | Extract text from a DOCX — Extract clean text from a Word .docx — for RAG, search and agents. | $0.002 | /v1/docx/text |
| docx_to_pdf | Convert a DOCX to PDF — Convert a Word .docx into a clean, print-styled PDF. | $0.01 | /v1/docx/pdf |
| data_to_spreadsheet | Create a spreadsheet from rows — Turn rows of JSON into a downloadable XLSX or CSV — the generation mirror of File → Markdown. | $0.002 | /v1/data/spreadsheet |
| file_to_markdown | Convert a file to Markdown — Convert a Word (.docx), Excel (.xlsx) or CSV file into clean Markdown — for RAG, agents and pipelines. | $0.002 | /v1/file/markdown |
| render_document | Generate a document — Render a branded PDF from a named template — invoice, receipt or report. Money computed for you. | $0.01 | /v1/document |
| read_url | Read a web page as Markdown — Render the live page and return clean, readable Markdown — for RAG, notes and agents. | $0.004 | /v1/web/markdown |
| scrape_page | Scrape a web page — One render → rendered HTML, every link, and page metadata. | $0.006 | /v1/web/scrape |
| url_to_pdf | Snapshot a web page as PDF — Snapshot the live, rendered page as a pixel-faithful PDF. | $0.01 | /v1/web/pdf |
| url_to_screenshot | Screenshot a web page — Capture the live page as a PNG — viewport or full scroll height. | $0.01 | /v1/web/screenshot |
| extract_data | Extract structured data — Name the fields you want — from a URL, PDF or Office file (.docx/.xlsx/.csv) — and get them back as structured JSON. | from $0.02 | /v1/extract |
| summarize_document | Summarize a document — AI summary of a web page, PDF, Office file or raw text — grounded, no fabrication. | varies | /v1/summarize |
| answer_from_document | Answer a question from a document — Ask a question and get an answer grounded ONLY in a URL, PDF, Office file or text. | varies | /v1/answer |
| batch_scrape | Batch: URLs to Markdown — Markdown for up to 10 URLs in one call. | $0.004 per URL | /v1/web/batch |
| crawl_site | Crawl a site to Markdown — The root page plus same-origin pages, all as Markdown. | $0.006 + $0.004 per page | /v1/web/crawl |
| map_site | Map a site's URLs — Discover the same-origin URLs on a page — the site map, no content fetched. | $0.006 | /v1/web/map |
Text results (Markdown, scrape data) return inline. File results (PDF, PNG) return a file_id for chaining between tools plus a download URL valid for one hour.
Good to know
Same meter, same limits
A tool call consumes exactly what its HTTP endpoint would: the same units, the same monthly cap, the same 60/min limit. There is nothing MCP-specific to buy or configure — one key covers both. Prices: /pricing.