MCP Server Playwright
by aptcats (Automata Labs)
MCP Server Playwright provides full browser automation capabilities using Playwright. It allows you to control a browser instance, capture screenshots, interact with web elements, and execute JavaScript within the browser context.
Last updated: N/A
What is MCP Server Playwright?
MCP Server Playwright is a server that exposes Playwright's browser automation features as a set of tools that can be integrated with other applications, such as Claude Desktop. It enables programmatic control of a browser for tasks like web scraping, UI testing, and generating screenshots.
How to use MCP Server Playwright?
The server can be installed using either npx or mcp-get. Once installed, it automatically configures itself within the Claude Desktop environment. You can then use the provided tools (e.g., browser_navigate, browser_screenshot, browser_click) by sending appropriately formatted JSON requests to the server.
Key features of MCP Server Playwright
Full browser automation capabilities
Screenshot capture of entire pages or specific elements
Comprehensive web interaction (navigation, clicking, form filling)
Console log monitoring
JavaScript execution in browser context
Use cases of MCP Server Playwright
Automated web scraping
UI testing
Generating website screenshots
Automating web-based tasks
Integrating browser functionality into other applications
FAQ from MCP Server Playwright
How do I install MCP Server Playwright?
How do I install MCP Server Playwright?
You can install it using either npx or mcp-get. Refer to the Installation section in the README for detailed instructions.
Where is the configuration file located?
Where is the configuration file located?
The configuration file is automatically created/updated at: Windows: %APPDATA%\Claude\claude_desktop_config.json or macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
What tools are available?
What tools are available?
The available tools include browser_navigate, browser_screenshot, browser_click, browser_click_text, browser_hover, browser_hover_text, browser_fill, browser_select, browser_select_text, and browser_evaluate.
How do I access screenshots?
How do I access screenshots?
Screenshots can be accessed via the screenshot://<n> resource, where <n> is the name specified during capture.
How do I access console logs?
How do I access console logs?
Console logs can be accessed via the console://logs resource.