MCP-Server-Playwright
目录
Related MCP server: Cloudflare Playwright MCP
特征
🌐 完整的浏览器自动化功能
📸 整个页面或特定元素的屏幕截图
🖱️ 全面的网页交互(导航、点击、表单填写)
📊 控制台日志监控
🔧 在浏览器上下文中执行 JavaScript
安装
通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装 MCP Server Playwright:
npx -y @smithery/cli install @automatalabs/mcp-server-playwright --client claude您可以使用 npx 或 mcp-get 安装该包:
使用 npx:
npx @automatalabs/mcp-server-playwright install此命令将:
检查您的操作系统兼容性(Windows/macOS)
创建或更新 Claude 配置文件
配置 Playwright 服务器集成
配置文件将在以下位置自动创建/更新:
Windows:
%APPDATA%\Claude\claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
使用 mcp-get:
npx @michaellatman/mcp-get@latest install @automatalabs/mcp-server-playwright配置
安装过程将自动将以下配置添加到您的 Claude 配置文件中:
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@automatalabs/mcp-server-playwright"]
}
}
}成分
工具
browser_navigate
导航到浏览器中的任意 URL
{
"url": "https://stealthbrowser.cloud"
}browser_screenshot
捕获整个页面或特定元素的屏幕截图
{
"name": "screenshot-name", // required
"selector": "#element-id", // optional
"fullPage": true // optional, default: false
}browser_click
使用 CSS 选择器单击页面上的元素
{
"selector": "#button-id"
}browser_click_text
根据文本内容点击页面上的元素
{
"text": "Click me"
}browser_hover
使用 CSS 选择器将鼠标悬停在页面上的元素上
{
"selector": "#menu-item"
}browser_hover_text
根据文本内容将鼠标悬停在页面上的元素上
{
"text": "Hover me"
}browser_fill
填写输入字段
{
"selector": "#input-field",
"value": "Hello World"
}browser_select
使用 CSS 选择器在 SELECT 元素中选择一个选项
{
"selector": "#dropdown",
"value": "option-value"
}browser_select_text
根据文本内容选择 SELECT 元素中的选项
{
"text": "Choose me",
"value": "option-value"
}browser_evaluate
在浏览器控制台中执行 JavaScript
{
"script": "document.title"
}资源
控制台日志(
console://logs)以文本格式访问浏览器控制台输出
包括来自浏览器的所有控制台消息
屏幕截图(
screenshot://<n>)访问捕获的屏幕截图的 PNG 图像
通过捕获期间指定的名称引用
执照
该项目根据 MIT 许可证获得许可 - 有关详细信息,请参阅LICENSE文件。
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables LLMs to perform web browsing tasks, take screenshots, and execute JavaScript using Puppeteer for browser automation.423,4061MIT
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to control a browser through a set of tools, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots.
- FlicenseNot gradedqualityCmaintenanceEnables AI assistants to control a browser through a set of tools, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots.
- AlicenseNot gradedqualityDmaintenanceEnables LLMs to perform browser automation tasks including web scraping, taking screenshots, and executing JavaScript using Playwright. It facilitates real-time interaction with web pages and the generation of automated test code.60MIT
Related MCP Connectors
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
E2LLM gives your AI eyes and hands in a real browser: structured perception (SiFR) plus action.
Enable language models to perform advanced AI-powered web scraping with enterprise-grade reliabili…
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/VikashLoomba/MCP-Server-Playwright'
If you have feedback or need assistance with the MCP directory API, please join our Discord server