by 详细分析 ▾
运行时依赖
版本
- Initial release of the playwright-mcp skill for browser automation via Playwright MCP server. - Provides tools to navigate websites, interact with forms, click elements, extract data, and take screenshots. - Supports command-line options for browser selection, headless mode, viewport sizing, security controls, and output management. - Includes detailed quick start and usage examples for common automation workflows. - Security features include restricted file system access, host validation, and sandboxing by default.
安装命令 点击复制
技能文档
Browser automation powered by Playwright MCP server. Control Chrome, Firefox, or WebKit programmatically.
Installation
npm install -g @playwright/mcp
# Or
npx @playwright/mcp
Install browsers (first time):
npx playwright install chromium
Quick 开始
开始 MCP Server (STDIO mode)
npx @playwright/mcp
开始 带有 Options
# Headless mode
npx @playwright/mcp --headless# Specific browser
npx @playwright/mcp --browser firefox
# With viewport
npx @playwright/mcp --viewport-size 1280x720
# Ignore HTTPS errors
npx @playwright/mcp --ignore-https-errors
Common 使用 Cases
1. Navigate 和 Extract Data
# MCP tools available:
# - browser_navigate: Open URL
# - browser_click: Click element
# - browser_type: Type text
# - browser_select_option: Select dropdown
# - browser_get_text: Extract text content
# - browser_evaluate: Run JavaScript
# - browser_snapshot: Get page structure
# - browser_close: Close browser
2. 表单 Interaction
1. browser_navigate to form URL
- browser_type into input fields
- browser_click to submit
- browser_get_text to verify result
3. Data Extraction
1. browser_navigate to page
- browser_evaluate to run extraction script
- Parse returned JSON data
MCP Tools Reference
| Tool | Description |
|---|---|
browser_navigate | Navigate to URL |
browser_click | Click element by selector |
browser_type | Type text into input |
browser_select_option | Select dropdown option |
browser_get_text | Get text content |
browser_evaluate | Execute JavaScript |
browser_snapshot | Get accessible page snapshot |
browser_close | Close browser context |
browser_choose_file | Upload file |
browser_press | Press keyboard key |
Configuration Options
# Security
--allowed-hosts example.com,api.example.com
--blocked-origins malicious.com
--ignore-https-errors# Browser settings
--browser chromium|firefox|webkit
--headless
--viewport-size 1920x1080
--user-agent "Custom Agent"
# Timeouts
--timeout-action 10000 # Action timeout (ms)
--timeout-navigation 30000 # Navigation timeout (ms)
# Output
--output-dir ./playwright-output
--save-trace
--save-video 1280x720
Examples
登录 到 Website
browser_navigate: { url: "https://example.com/login" }
browser_type: { selector: "#username", text: "user" }
browser_type: { selector: "#password", text: "pass" }
browser_click: { selector: "#submit" }
browser_get_text: { selector: ".welcome-message" }
Extract 表 Data
browser_navigate: { url: "https://example.com/data" }
browser_evaluate: {
script: "() => { return Array.from(document.querySelectorAll('table tr')).map(r => r.textContent); }"
}
Screenshot
browser_navigate: { url: "https://example.com" }
browser_evaluate: { script: "() => { document.body.style.zoom = 1; return true; }" }
# Screenshot saved via --output-dir or returned in response
Security Notes
- 由 默认 restricts file system access 到 workspace root
- Host validation prevents 导航 到 untrusted domains
- Sandboxing 已启用 由 默认 (使用
--否-sandbox带有 caution) - 服务 workers blocked 由 默认
Troubleshooting
# Update browsers
npx playwright install chromium# Debug mode
npx @playwright/mcp --headless=false --output-mode=stdout
# Check installation
playwright-mcp --version
Links
免费技能或插件可能存在安全风险，如需更匹配、更安全的方案，建议联系付费定制