Playwright Browser Automation

Playwright MCP is a server implementation that enables AI assistants to control web browsers through the Model Context Protocol. It provides tools for navigating websites, capturing page snapshots, interacting with elements, and taking screenshots - all accessible via standardized MCP interfaces. The server offers two modes: a snapshot-based approach that uses accessibility trees for better semantic understanding of web pages, and a vision-based mode that works with screenshots for visual interactions. Built by Microsoft, this implementation leverages Playwright's automation capabilities to allow AI assistants to perform complex web tasks like form filling, clicking elements, and extracting information from websites.

Source

Repository: https://github.com/microsoft/playwright-mcp