playwright-browser

Headless browser via Playwright. Scrapes JS-rendered pages, takes screenshots, extracts links and tables, fills forms, runs arbitrary JS. Useful when fetch() is not enough.

Playwright

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

模型生成摘要（rules/v1 · 2026-10-01 11:55）：Headless browser via Playwright
这是模型对公开材料的总结，不是官方声明，请以原链内容为准。

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://rab-browser.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "playwright-browser": {
      "url": "https://rab-browser.run.tools"
    }
  }
}

能力清单

工具	说明
scrape_url	Scrape a URL and return page content: title, text, HTML, and metadata. Handles JavaScript-rendered pages, SPAs, and dynamic content that simple HTTP fetchers cannot access.
take_screenshot	Take a screenshot of any URL and return it as base64-encoded JPEG. Useful for visual verification, capturing UI state, or getting screenshots of web apps.
extract_links	Extract all hyperlinks from a URL. Returns list of {text, href, is_external} objects. Useful for crawling, sitemap analysis, or finding related resources.
extract_tables	Extract all HTML tables from a URL as structured JSON data. Perfect for scraping data from HTML tables, financial data, sports stats, product comparisons.
fill_form	Navigate to a URL, fill form fields, and optionally submit. Returns the page content after form interaction. Useful for automating web forms, searches, logins.
run_js	Navigate to a URL and execute custom JavaScript on the page. Returns the result of the script. Useful for complex data extraction, interacting with page state, or testing.

playwright-browser

接入信息

能力清单

相关资产

rove

autoapply-mcp

TestForge - Autonomous Full-Stack QA, E2E Playwright & Vitest Engine MCP

playwright-e2e-mcp

Playwright 网页自动化工具

axelhu-playwright-scrape