広告掲載
MCP.so
ログイン

Webpage Screenshot MCP Server

@ananddtyagi

リポジトリ

基本情報

カテゴリ

ブラウザ自動化

ライセンス

MIT

トランスポート

stdio

作者

ananddtyagi

Webpage Screenshot MCP Server について

An MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.

Webpage Screenshot MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "webpage-screenshot": {
      "command": "node",
      "args": [
        "~/path/to/webpage-screenshot-mcp/dist/index.js"
      ]
    }
  }
}

Webpage Screenshot MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Webpage Screenshot MCP Server?

Webpage Screenshot MCP Server is an MCP server that captures screenshots of web pages using Puppeteer. It allows AI agents to visually verify web applications and see their progress when generating web apps.

How to use Webpage Screenshot MCP Server?

Install dependencies with npm install, build with npm run build, then add the server configuration (command node with path to dist/index.js) to Claude Desktop or Cursor settings. Use the provided tools: login-and-wait, screenshot-page, screenshot-element, and clear-auth-cookies.

Key features of Webpage Screenshot MCP Server

  • Full page or viewport screenshots
  • Element-specific screenshots via CSS selectors
  • Supports PNG, JPEG, and WebP formats
  • Base64 encoded image output
  • Manual login with cookie persistence
  • Default browser integration for existing sessions
  • Session persistence for multi-step workflows

Use cases of Webpage Screenshot MCP Server

  • Visually verify a web application during development
  • Take screenshots of protected pages after manual login
  • Capture specific UI elements for testing or documentation
  • Automate multi-step workflows that require authentication
  • Inspect a website’s appearance with your default browser

よくある質問

1

What does this server do?

It provides MCP tools to capture screenshots of web pages (full page, viewport, or specific elements) and return them as base64 encoded images, with support for authentication and session persistence.

2

How does authentication work?

Use the `login-and-wait` tool to manually log in through a visible browser window; cookies are saved automatically and reused in subsequent `screenshot-page` or `screenshot-element` calls when `useSavedAuth` is true.

3

What are the runtime requirements?

Node.js is required. The server uses Puppeteer (bundled Chromium) by default, but can also connect to your system’s default browser (Chrome, Edge, or Safari) with `useDefaultBrowser: true`.

4

What is the difference between headless and visible mode?

Headless mode (`visibleBrowser: false`) is faster for automation; visible mode (`visibleBrowser: true`) shows the browser window, required for `useDefaultBrowser` and manual interactions.

5

Where are authentication cookies stored?

Cookies are saved to the `.mcp-screenshot-cookies` directory in your home folder. They can be cleared per domain or globally using the `clear-auth-cookies` tool.

コメント

「ブラウザ自動化」の他のコンテンツ

BitBrowser MCP service

BitBrowser01

BitBrowser MCP simple to use, no complicated procedures required. Supports a variety of intelligent agent services.

Scrapling Fetch MCP

cyberchitta

Helps AI assistants access text content from bot-protected websites. MCP server that fetches HTML/markdown from sites with anti-automation measures using Scrapling.

101

HTML/CSS to Image

An MCP server for generating images from HTML & CSS or screenshots of URLs using htmlcsstoimage.com.

Puppeteer MCP Server

merajmehrabi

This MCP server provides browser automation capabilities through Puppeteer, allowing interaction with both new browser instances and existing Chrome windows.

474

Fastcrw

us

Fast, lightweight Firecrawl/Tavily alternative in Rust. Web scraper, crawler & search API with MCP server for AI agents. Drop-in Firecrawl-compatible API (/scrape, /crawl, /search). 2.3x faster than Tavily, 1.5x faster than Firecrawl in 1K-URL benchmarks. 6 MB RAM, single binary.

286
広告掲載