Playwright MCP
Level ACuratedOfficialLocal微软出品的浏览器自动化工具,用结构化快照操控网页:点击、填表、截图、抓取,无需视觉模型
Overview
Microsoft’s Playwright MCP drives browser automation via structured page snapshots—click, fill, screenshot, and scrape—so agents can control pages without a vision model.
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/microsoft/playwright-mcp
Known working client config (can write into mcp.json):
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"@playwright/mcp@latest"
]
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
mcp-for-beginnersThis open-source curriculum introduces the fundamentals of Model Context Protocoflint-chart🪄 Flint is a visualization language that lets AI agents reliably create expressiScrapling🕷️ The BEST Web Scraping framework that handles everything from a single requestChrome DevTools MCP谷歌官方:让 AI 操控 Chrome——页面操作、Lighthouse 性能分析、网络监控、控制台日志UI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models andcuaScale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchma