Playwright MCP Server
Browser Automationstdiov0.1.5
Microsoft's official Playwright MCP server that provides browser automation capabilities for AI agents. Enables navigating web pages, clicking elements, filling forms, taking screenshots, and extracting content. Supports headless and headed modes with Chromium, Firefox, and WebKit browsers. Ideal for web testing, scraping, and interactive browsing tasks.
连接
将此配置添加到 .claude/mcp.json
{
"mcpServers": {
"playwright": {
"command": "npx",
"args": [
"-y",
"@playwright/mcp"
]
}
}
}工具 (5)
browser_navigate
Navigate the browser to a specified URL.
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "URL to navigate to"
}
}
}browser_click
Click an element on the page using a CSS or text selector.
{
"type": "object",
"required": [
"selector"
],
"properties": {
"selector": {
"type": "string",
"description": "CSS selector or text content to identify the element"
}
}
}browser_fill
Fill an input field with text.
{
"type": "object",
"required": [
"selector",
"value"
],
"properties": {
"value": {
"type": "string",
"description": "Text to fill into the input"
},
"selector": {
"type": "string",
"description": "CSS selector for the input element"
}
}
}browser_screenshot
Take a screenshot of the current page or a specific element.
{
"type": "object",
"properties": {
"selector": {
"type": "string",
"description": "Optional CSS selector to screenshot a specific element"
}
}
}browser_get_text
Extract text content from the page or a specific element.
{
"type": "object",
"properties": {
"selector": {
"type": "string",
"description": "Optional CSS selector to extract text from"
}
}
}资源
此服务器未提供任何资源。
提示词
此服务器未提供任何提示词。
服务器信息
- 许可证
- Apache-2.0
- 版本
- 0.1.5
- 星标
- 32,997
- 最后更新
- 2026年5月25日