Screenshot & PDF Capture API

io.github.Br0ski777由 GitHub 账号 Br0ski777 发布v1.2.0更新于 Oct 28, 2026

Capture screenshots (PNG/JPEG/WebP) and generate PDFs from any URL. x402 payments.

发布方自己的服务:screenshot.com.ar

已验证SSE可网页运行浏览器自动化媒体与设计

概览

AI 生成的概览

远程 MCP 端点,用 Chromium 渲染任意网址并返回截图图片或分页 PDF,按次以 USDC 付费。

可以做什么
  • 截取任意网址的截图,支持 PNG、JPEG、WebP 格式,可设置视口宽高与整页模式
  • 把在线网页转换为可打印的 PDF,可指定纸张格式
  • 两类操作均提供 GET 与 POST 两种调用方式,参数相同
  • 返回二进制图片或 PDF 内容,而非抽取的文本
适用场景
适合视觉质量检查与响应式设计验证、生成网页缩略图、把网页存档为图片或 PDF,以及从网址保存收据、发票或文章。不适用于文本抽取,也不用于把自有 HTML 或 Markdown 生成 PDF。
运行要求
远程 MCP 端点,无需本地安装。无需 API 密钥或注册,但每次调用都通过 x402 协议以 Base L2 上的 USDC 按次付费,因此需要支持 x402 的客户端和已充值的钱包。需要能访问服务商端点的网络。
安装前请注意
每次调用都会产生费用(截图 0.015 美元、PDF 0.02 美元),并通过加密钱包以 Base 上的 USDC 结算,服务器本身不设消费上限。提交的网址会由第三方服务抓取,该服务能看到所请求的页面。支付流程交由 x402 客户端与结算方处理。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Screenshot & PDF Capture API,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 SSE。 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/io.github.Br0ski777%2Fscreenshot-pdf/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": {
    "screenshot-pdf-capture-api": {
      "type": "sse",
      "url": "https://screenshot-pdf.api.klymax402.com/mcp"
    }
  }
}

README

Screenshot & PDF Capture API

[MCP Server] [x402] [License: MIT]

Capture full-page screenshots and PDFs from any URL. Chromium rendering, custom viewport, PNG/JPEG/WebP output. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.

Part of the klymax402 marketplace -- 100 x402 micropayment APIs for AI agents, one wallet, USDC on Base.

Quickstart -- MCP

Add to your MCP client config (Claude Desktop, Cursor, ElizaOS, etc.):

json
{  "mcpServers": {    "screenshot-pdf": {      "url": "https://screenshot-pdf.api.klymax402.com/mcp"    }  }}

Quickstart -- HTTP (x402)

bash
curl "https://screenshot-pdf.api.klymax402.com/api/screenshot?url=https://example.com"# -> 402 Payment Required, with an x402 payment challenge in the response body

Any x402-aware client (@x402/fetch, x402-agent-tools, ATXP) handles the 402 -> sign -> retry cycle automatically.

Tools

ToolMethodPathPriceDescription
capture_screenshotGET/api/screenshot$0.015Capture a screenshot of any URL
capture_screenshotPOST/api/screenshot$0.015Capture a screenshot of any URL (POST variant)
webpage_to_pdfGET/api/pdf$0.02Generate a PDF from any URL
webpage_to_pdfPOST/api/pdf$0.02Generate a PDF from any URL (POST variant)

capture_screenshot

Use this when you need a visual capture of a web page. Renders in a real Chromium browser and returns an image.

Parameters

NameTypeRequiredDescription
urlstringyesURL to screenshot (e.g. https://example.com)
widthnumbernoViewport width in px (default: 1280)
heightnumbernoViewport height in px (default: 720)
fullPagebooleannoCapture full scrollable page (default: false)
formatstringnoImage format (default: png)

Example response:

json
binary image file with Content-Type image/png, typical size 200-800KB for a full page.

When to use: visual QA testing, generating page thumbnails, archiving web pages, or verifying responsive design. Essential for automated screenshot pipelines and visual regression testing.

Not for: text extraction (use web_scrape_to_markdown), PDF from data (use document_generate_pdf), PDF from URL (use webpage_to_pdf).

capture_screenshot

Use this when you need a visual capture of a web page. Renders in a real Chromium browser and returns an image. POST variant of capture_screenshot -- same params passed as JSON body instead of query string.

Parameters

NameTypeRequiredDescription
urlstringyesURL to screenshot (e.g. https://example.com)
widthnumbernoViewport width in px (default: 1280)
heightnumbernoViewport height in px (default: 720)
fullPagebooleannoCapture full scrollable page (default: false)
formatstringnoImage format (default: png)

Example response:

json
binary image file with Content-Type image/png, typical size 200-800KB for a full page.

When to use: visual QA testing, generating page thumbnails, archiving web pages, or verifying responsive design. Essential for automated screenshot pipelines and visual regression testing.

Not for: text extraction (use web_scrape_to_markdown), PDF from data (use document_generate_pdf), PDF from URL (use webpage_to_pdf).

webpage_to_pdf

Use this when you need to convert a live web page to a printable PDF document. Renders in a real Chromium browser and returns binary PDF.

Parameters

NameTypeRequiredDescription
urlstringyesURL to convert to PDF (e.g. https://example.com)
formatstringnoPaper format (default: A4)

Example response:

json
binary PDF file with Content-Type application/pdf, properly paginated with headers/footers.

When to use: archiving web pages as PDF, generating printable articles, saving receipts or invoices from URLs, or creating offline documentation snapshots.

Not for: custom documents from HTML/Markdown (use document_generate_pdf), screenshots (use capture_screenshot), web scraping text (use web_scrape_to_markdown).

webpage_to_pdf

Use this when you need to convert a live web page to a printable PDF document. Renders in a real Chromium browser and returns binary PDF. POST variant of webpage_to_pdf -- same params passed as JSON body instead of query string.

Parameters

NameTypeRequiredDescription
urlstringyesURL to convert to PDF (e.g. https://example.com)
formatstringnoPaper format (default: A4)

Example response:

json
binary PDF file with Content-Type application/pdf, properly paginated with headers/footers.

When to use: archiving web pages as PDF, generating printable articles, saving receipts or invoices from URLs, or creating offline documentation snapshots.

Not for: custom documents from HTML/Markdown (use document_generate_pdf), screenshots (use capture_screenshot), web scraping text (use web_scrape_to_markdown).

Example agent prompts

  • "A visual capture of a web page"
  • "A visual capture of a web page"
  • "Convert a live web page to a printable PDF document"

Payment

  • Protocol: x402 -- HTTP-native pay-per-call, no signup, no API key
  • Network: Base L2 (eip155:8453)
  • Asset: USDC
  • Facilitator: Coinbase CDP (primary), PayAI (fallback)
  • Also reachable via ATXP (OAuth-wrapped x402, RFC 9728 protected-resource metadata)

Part of klymax402

100 x402 micropayment APIs for AI agents -- one wallet, USDC on Base, zero signup.

License

MIT

来源:README.md,提交 d079418

工具

0
SourceWeft 尚未读取此服务器的工具。

版本历史

1
  1. v1.2.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

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

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式必需10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

其他 Screenshot 集成