Playwright Server MCP
Playwright Server MCP
一个基于Playwright的MCP服务器,提供浏览器自动化能力
组件
资源
服务器实现了简单的笔记存储系统:
自定义note://URI方案用于访问单个笔记
每个笔记资源具有名称、描述和text/plain MIME类型
提示
服务器提供单个提示功能:
summarize-notes: 创建所有存储笔记的摘要
可选"style"参数控制详细程度(brief/detailed)
生成结合所有当前笔记与样式偏好的提示
工具
服务器实现以下Playwright相关工具:
会话与导航
playwright_new_session: 创建新的浏览器会话并打开浏览器窗口可选
url参数(字符串),指定初始访问网址,不填则只打开浏览器
playwright_navigate: 导航到指定网址需要
url参数(字符串),如不包含http或https前缀将自动添加https://如果没有活跃的浏览器会话,会自动创建一个新会话
页面交互与获取内容
playwright_screenshot: 对当前页面或特定元素进行截图需要
name参数(字符串),截图文件名称,不需要包含扩展名可选
selector参数(字符串),CSS选择器用于指定要截图的页面元素,不填则截取整个页面
playwright_evaluate: 在浏览器控制台中执行JavaScript代码需要
script参数(字符串),需要在浏览器中执行的JavaScript代码
playwright_get_text_content: 获取当前页面中所有可见元素的文本内容无需参数
智能过滤重复内容,只返回有意义的文本
playwright_get_html_content: 获取页面中指定元素的HTML内容需要
selector参数(字符串),CSS选择器用于定位需要获取HTML内容的页面元素
高级交互操作
playwright_action: 支持丰富的元素选择与交互方式必需参数:
by: 选择元素方式,支持get_by_text、get_by_placeholder、get_by_label、get_by_role等by_value: 选择元素的值action: 操作类型,如fill、click、dblclick、hover、check等
可选参数:
value: 操作的值force: 是否强制执行动作delay: 按键之间的延迟(毫秒)以及更多专用参数,参见代码文档
配置
系统要求
Python 3.10+
Playwright 1.44+
快速开始
安装
Claude Desktop配置
MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
"playwright-server": {
"command": "uv",
"args": [
"--directory",
"C:\\Users\\xxxxx\\Documents\\project\\python\\mcp\\playwright-server",
"run",
"playwright-server"
]
}
}"mcpServers": {
"playwright-server": {
"command": "uvx",
"args": [
"playwright-server"
]
}
}开发
构建与发布
准备发布包:
同步依赖并更新锁定文件:
uv sync构建包分发:
uv build这将在dist/目录中创建源代码和wheel分发。
发布到PyPI:
uv publish注意: 您需要通过环境变量或命令参数设置PyPI凭据:
令牌:
--token或UV_PUBLISH_TOKEN或用户名/密码:
--username/UV_PUBLISH_USERNAME和--password/UV_PUBLISH_PASSWORD
调试
由于MCP服务器通过stdio运行,调试可能具有挑战性。为获得最佳调试体验,我们强烈推荐使用MCP Inspector。
您可以通过npm使用以下命令启动MCP Inspector:
npx @modelcontextprotocol/inspector uv --directory C:\Users\xxxxx\Documents\project\python\mcp\playwright-server run playwright-server启动后,Inspector将显示一个URL,您可以在浏览器中访问该URL开始调试。
使用示例
基本网页访问与截图
# 创建会话并导航到指定网址
await playwright_navigate(url="example.com")
# 截取整个页面
await playwright_screenshot(name="fullpage")
# 截取特定元素
await playwright_screenshot(name="logo", selector=".logo")高级交互操作
# 点击文本匹配的按钮
await playwright_action(by="get_by_text", by_value="登录", action="click")
# 填充表单字段
await playwright_action(by="get_by_placeholder", by_value="用户名", action="fill", value="test@example.com")
# 检查元素是否可见
await playwright_action(by="get_by_test_id", by_value="submit-button", action="is_visible")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/ziux/playwright-plus-python-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server