MCP Servers / web-scraping / Playwright Server

Playwright Server

JSON →
stdiononeweb-scraping

A server for browser automation using the Playwright library.

Install
How to run this server
[ { "cmd": "npx @modelcontextprotocol/inspector", "imports": [] } ]
server path: playwright-server
Tools
What this server exposes
playwright_new_session
创建新的浏览器会话并打开浏览器窗口,可选url参数指定初始访问网址
playwright_navigate
导航到指定网址,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
playwright_screenshot
对当前页面或特定元素进行截图,需要name参数,可选selector参数指定CSS选择器
playwright_evaluate
在浏览器控制台中执行JavaScript代码,需要script参数
playwright_get_text_content
获取当前页面中所有可见元素的文本内容,智能过滤重复内容
playwright_get_html_content
获取页面中指定元素的HTML内容,需要selector参数
playwright_action
支持丰富的元素选择与交互方式,包括get_by_text、get_by_placeholder、get_by_label、get_by_role等选择方式,支持fill、click、dblclick、hover、check等操作
Configuration
Environment & auth
authnone
envUV_PUBLISH_TOKEN
Resources
Playwright Server — MCP Server · libregistry