PreteWorks API

com.preteworks由 preteworks.com 发布官方发布者v1.0.2更新于 Oct 24, 2026

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

已验证Streamable HTTP可网页运行网页搜索与抓取文件与存储AI 与机器学习

概览

AI 生成的概览

一个托管的文档与网页处理 API，让助手抓取网页、用 AI 提取或总结内容，并生成、编辑和填写 PDF。

可以做什么
将 HTML、Markdown、结构化文档和图片渲染为 PDF，把 DOCX 转为 PDF 或文本，把 Office 文件转为 Markdown 或表格，并把数据生成 XLSX 或 CSV 文件。编辑 PDF：合并、拆分、选取或旋转页面，添加页码、水印和元数据，读取并填写表单字段。读取 PDF 元数据并提取 PDF 文本，用于搜索或摘要。抓取公开网址，返回 Markdown、HTML、链接、元数据、截图或 PDF，并可批量抓取或爬取站内链接页面。用 AI 从网页、PDF、Office 文件或纯文本中提取指定字段、生成摘要，或仅依据该来源回答问题。
适用场景
适合需要把网页或文档转成可读文本或 PDF、拼接与整理 PDF、填写 PDF 表单，或对给定来源做 AI 字段提取与问答的场景。适用于资料研究、RAG 准备和文档生成，无需在本地运行转换库。
运行要求
远程 streamable HTTP 端点 api.preteworks.com。需要在 Authorization 请求头中提供 bearer API 密钥，密钥来自注册页面；免费额度标注为每月 500 单位且无需信用卡。需要网络访问；生成的文件以文件 ID 加约一小时有效的下载链接返回。
安装前请注意
API 密钥是敏感凭据，通过 Authorization 请求头发送；用量按单位计费，使用较多时可能需要付费方案。提交的文档、网址和文本会由第三方服务处理，AI 工具会把内容发送到该服务进行提取、摘要和问答。生成的下载链接约一小时后失效。抓取仅限公开主机，私有和内部地址会被阻止。

安装

在 SourceWeft 中

  1. 打开 控制台中的 PreteWorks API，将其添加到工作区。
  2. 连接 Authorization token 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.preteworks%2Fpreteworks-api/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "preteworks-api": {
      "type": "http",
      "url": "https://api.preteworks.com/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

工具

29

render_html_to_pdf

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.

输入参数html必填

number_pdf

Number PDF pages

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.

输入参数pdf必填startformatposition

pdf_info

Read PDF info

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

输入参数pdf必填

set_pdf_metadata

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.

输入参数pdf必填titleauthorcreatorsubjectkeywords

render_document

Generate a 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.

输入参数data必填template必填

merge_pdfs

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.

输入参数pdfs必填

select_pages

Select PDF 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.

输入参数pdf必填pages必填

rotate_pdf

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.

输入参数pdf必填degrees必填

watermark_pdf

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.

输入参数pdf必填text必填

extract_pdf_text

Extract text from a PDF

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.

输入参数pdf必填

images_to_pdf

Images to PDF

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

输入参数images必填

markdown_to_pdf

Render Markdown to PDF

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

输入参数titlemarkdown必填

split_pdf

Split a 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.

输入参数pdf必填ranges

read_pdf_form

Read a PDF form

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

输入参数pdf必填

fill_pdf_form

Fill a PDF form

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

输入参数pdf必填fields必填flatten

file_to_markdown

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' (docx|xlsx|csv) overrides auto-detection.

输入参数file必填format

data_to_spreadsheet

Create a spreadsheet from rows

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.

输入参数rows必填formatsheet_name

batch_scrape

Batch: URLs to Markdown

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.

输入参数urls必填

crawl_site

Crawl a site to Markdown

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.

输入参数url必填limit

map_site

Map a site's URLs

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

输入参数url必填

extract_data

Extract structured data (AI)

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.

输入参数pdfurlfilefields必填

summarize_document

Summarize a document (AI)

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.

输入参数pdfurlfiletextmax_words

answer_from_document

Answer a question from a document (AI)

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.

输入参数pdfurlfiletextquestion必填

docx_to_text

DOCX to text

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

输入参数docx必填

docx_to_pdf

DOCX to PDF

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

输入参数docx必填

read_url

Read a web page as Markdown

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.

输入参数url必填

url_to_pdf

Snapshot a web page as 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.

输入参数url必填

url_to_screenshot

Screenshot a web page

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.

输入参数url必填full_page

scrape_page

Scrape a web page (HTML + links + metadata)

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.

输入参数url必填formats

版本历史

1
  1. v1.0.2最新Sep 16, 2026

评分

已满足适用检查项的 72%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分

    请在注册中心条目中发布图标。

  • 文档15 分

    请声明包含 README 的 GitHub 仓库，或在 OAuth 受保护资源元数据中提供 resource_documentation。

  • 许可证不适用

    托管服务按其提供方的条款使用，因此这里不要求许可证。此检查项不计入百分比。