Browser Automation MCP Servers

Find MCP servers that let agents open websites, inspect pages, capture screenshots, scrape data, and run repeatable browser tasks.

サーバーを比較Browser automation を検索

一致する MCP サーバー

既存の MCP Servers ディレクトリから取得しており、個別のトピックデータベースはありません。

すべての検索結果を見る
YetiBrowser MCP
公式
YetiBrowser MCP is a fully open-source solution to allow AI assistants to easily interact with your existing browser
サーバーを見る
Browser MCP
Control your real Chrome from Claude Code. 29 tools including CAPTCHA solving, file upload, multi-session, and human-in-the-loop.
サーバーを見る
Browser MCP
An MCP server that allows AI applications to control your browser.
サーバーを見る
Browser MCP
Browser MCP server for AI agents to automate web pages with Puppeteer, accessibility-tree actions, optional vision mode, and cross-platform browser control.
サーバーを見る
Browser MCP
Automate your local browser
サーバーを見る
BrowserCat MCP Server
Remote browser automation using the BrowserCat API.
サーバーを見る
Browser Control MCP
Enables AI agents to control a local browser, manage tabs, and conduct research via a browser extension.
サーバーを見る
browser-devtools-mcp
A Playwright-based MCP server that exposes a live browser as a traceable, inspectable, debuggable and controllable execution environment for AI agents.
サーバーを見る
Blueprint MCP
公式
Browser automation via MCP for Chrome and Firefox
サーバーを見る
Skyvern
公式
AI-powered browser automation MCP server — navigate sites, fill forms, extract data, and handle logins via Claude Code CLI
サーバーを見る
BrowserAct Skills
BrowserAct Skills is a curated directory for AI agent skills, including browser automation workflows and reusable agent capabilities. It helps developers discover practical skills for coding agents, MCP workflows, browser automation, testing, and web data workflows.
サーバーを見る
Unchained Sky
Browser automation MCP server that connects AI agents to your real Chrome browser with structured page understanding in ~500 tokens
サーバーを見る

Browser Automation MCP が適した場面

Give agents a real browser for QA, research, screenshots, and page inspection.

Automate navigation, clicks, form flows, and visual checks from an MCP-compatible client.

Choose between general browser control, Playwright workflows, Puppeteer automation, and DevTools inspection.

セットアップチェックリスト

  1. 1Choose a browser automation server based on the actions and browser engine you need.
  2. 2Install the server package or follow the repository setup instructions.
  3. 3Add the command or remote endpoint to your MCP client configuration.
  4. 4Verify a small navigation, screenshot, and page-inspection task before relying on longer workflows.

選び方

  • Check support for screenshots, DOM or accessibility snapshots, console logs, network data, and JavaScript execution.
  • Prefer servers with clear sandboxing, browser session, and permission behavior.
  • Use Playwright or Chrome DevTools specific servers when your workflow depends on those exact APIs.

Browser Automation MCP FAQ

What is Browser Automation MCP?

Browser Automation MCP connects an AI client to a browser automation layer so agents can navigate pages, inspect UI state, capture screenshots, and run browser tasks through MCP.

Is Browser Automation MCP only for testing?

No. Testing is common, but the same capability is useful for web research, scraping, visual QA, debugging, and workflows where an agent needs to interact with real websites.

Should I choose Playwright MCP or a general browser MCP server?

Use Playwright MCP when you specifically want Playwright actions and repeatable test-style flows. Use a broader browser MCP server when you need discovery, screenshots, or page inspection across a wider workflow.