PreteWorks API MCP server

Connect PreteWorks API and your agent gets 29 tools, among them answer_from_document, batch_scrape, crawl_site. It answers at https://api.preteworks.com/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 10 September 2026; the last check, on 19 October 2026, succeeded.

Status

Answering

Tools

Official

yes, served from preteworks.com

Reliability

6 of 6 checks

Response time

526 ms

Transport

streamable HTTP

Last checked

19 October 2026

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

Description as the publisher wrote it.

The 29 tools PreteWorks API offers

Tool	What it does
`answer_from_document`	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. Inputs: question, url, pdf, file, text
`batch_scrape`	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. Inputs: urls
`crawl_site`	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. Inputs: url, limit
`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. Inputs: rows, format, sheet_name
`docx_to_pdf`	Convert a .docx document (base64) to a PDF. Returns a file_id and a ~1h URL. Inputs: docx
`docx_to_text`	Extract the text of a .docx document (base64). Returns the text inline. Inputs: docx
`extract_data`	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 Inputs: fields, url, pdf, file
`extract_pdf_text`	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. Inputs: pdf
`file_to_markdown`	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 Inputs: file, format
`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. Inputs: pdf, fields, flatten
`images_to_pdf`	Combine PNG/JPEG images (base64) into a PDF, one image per page. Returns a file_id and a ~1h URL. Inputs: images
`map_site`	Discover the same-origin URLs linked from a page — the site map, with no page content fetched. Private/internal hosts are blocked. Inputs: url
`markdown_to_pdf`	Render Markdown to a clean, print-styled PDF. Returns a file_id and a ~1h URL. Inputs: markdown, title
`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. Inputs: pdfs
`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. Inputs: pdf, position, start, format
`pdf_info`	Read a PDF's metadata (title, author, subject, keywords, creator, producer, dates) plus page count and page size, as JSON. Inputs: pdf
`read_pdf_form`	List a PDF's form fields (name, type, value, options) as JSON. Inputs: pdf
`read_url`	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. Inputs: url
`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. Inputs: template, data
`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. Inputs: html
`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. Inputs: pdf, degrees
`scrape_page`	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 blocke Inputs: url, formats
`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. Inputs: pdf, pages
`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. Inputs: pdf, title, author, subject, keywords, creator
`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. Inputs: pdf, ranges
`summarize_document`	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. Inputs: url, pdf, file, text, max_words
`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. Inputs: url
`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. Inputs: url, full_page
`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. Inputs: pdf, text

Add PreteWorks API to your AI client

Every block below points at https://api.preteworks.com/mcp. Pick your client and copy.

Claude Code: one command in your terminal

claude mcp add --transport http preteworks-api https://api.preteworks.com/mcp

Claude Desktop: claude_desktop_config.json

{
  "mcpServers": {
    "preteworks-api": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.preteworks.com/mcp"]
    }
  }
}

Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project

{
  "mcpServers": {
    "preteworks-api": {
      "url": "https://api.preteworks.com/mcp"
    }
  }
}

VS Code and GitHub Copilot: .vscode/mcp.json

{
  "servers": {
    "preteworks-api": {
      "type": "http",
      "url": "https://api.preteworks.com/mcp"
    }
  }
}

Zed: Zed settings.json

{
  "context_servers": {
    "preteworks-api": {
      "url": "https://api.preteworks.com/mcp"
    }
  }
}

Windsurf: ~/.codeium/mcp_config.json

{
  "mcpServers": {
    "preteworks-api": {
      "serverUrl": "https://api.preteworks.com/mcp"
    }
  }
}

JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON

{
  "mcpServers": {
    "preteworks-api": {
      "url": "https://api.preteworks.com/mcp"
    }
  }
}

Continue: .continue/mcpServers/neuronto.yaml

name: PreteWorks API
version: 0.0.1
schema: v1
mcpServers:
  - name: PreteWorks API
    type: streamable-http
    url: https://api.preteworks.com/mcp

Gemini CLI: ~/.gemini/settings.json

{
  "mcpServers": {
    "preteworks-api": {
      "httpUrl": "https://api.preteworks.com/mcp"
    }
  }
}

Codex CLI: MCP server config

{
  "mcpServers": {
    "preteworks-api": {
      "type": "http",
      "url": "https://api.preteworks.com/mcp"
    }
  }
}

Warp: MCP servers, + Add, paste JSON

{
  "mcpServers": {
    "preteworks-api": {
      "url": "https://api.preteworks.com/mcp"
    }
  }
}

Goose: a one-click extension link

goose://extension?url=https%3A%2F%2Fapi.preteworks.com%2Fmcp&type=streamable_http&id=preteworks-api&name=PreteWorks%20API

Is PreteWorks API up right now?

It answered our last check on 19 October 2026 in 526 ms. Over 6 checks since 10 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to PreteWorks API

FileToPDF4 tools Pdf Tools10 tools Docimprint API22 tools Document Processing9 tools Mdtidy0 tools io.github.NicolasMartalog/docweave-mcp2 tools

Questions about PreteWorks API

Is there an official PreteWorks API MCP server?

Yes. It is published by preteworks.com and served from api.preteworks.com, the vendor's own domain: https://api.preteworks.com/mcp.

How many tools does PreteWorks API have?

29, as returned by the server's own tools/list on 11 September 2026: answer_from_document, batch_scrape, crawl_site, data_to_spreadsheet, docx_to_pdf, docx_to_text, extract_data, extract_pdf_text, and 21 more.

Is PreteWorks API down?

It answered our last check on 19 October 2026 in 526 ms. Over 6 checks since 10 September 2026 it answered 6.

How do I add PreteWorks API to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.preteworks.com/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does PreteWorks API need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: com.preteworks. Endpoint host: api.preteworks.com. ARD identifier: urn:air:com.preteworks:mcp:preteworks-api. First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.