A Model Context Protocol server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages, take screenshots, generate test code, web scraps the page and execute JavaScript in a real browser environment.
playwright_navigate - Navigate to a specified URLplaywright_screenshot - Take screenshots of pages or elementsplaywright_click - Click page elementsplaywright_iframe_click - Click elements within iframesplaywright_fill - Fill input fieldsplaywright_select - Select dropdown menu optionsplaywright_hover - Hover over elementsplaywright_evaluate - Execute JavaScript codeplaywright_close - Close the browserplaywright_expect_response - Wait for HTTP responsesplaywright_assert_response - Validate HTTP responsesplaywright_custom_user_agent - Set custom User Agentplaywright_get_visible_text - Get visible page textplaywright_get_visible_html - Get page HTML contentplaywright_go_back - Browser back navigationplaywright_go_forward - Browser forward navigationplaywright_drag - Drag and drop elementsplaywright_press_key - Keyboard key operationsplaywright_save_as_pdf - Save page as PDFplaywright_get - Execute HTTP GET requestsplaywright_post - Execute HTTP POST requestsplaywright_put - Execute HTTP PUT requestsplaywright_delete - Execute HTTP DELETE requestsplaywright_patch - Execute HTTP PATCH requestsstart_codegen_session - Start code generation sessionend_codegen_session - End code generation sessionget_codegen_session - Get code generation session infoclear_codegen_session - Clear code generation session{
"mcpServers": {
"playwright": {
"command": "npx",
"args": ["-y", "@executeautomation/playwright-mcp-server"]
}
}
}