Playwright Mcp

Brings Playwright's browser automation into your MCP workflow without needing vision models or screenshots. Instead of pixel-based approaches, it exposes structured accessibility tree data that LLMs can read and act on directly. You get deterministic web interactions through tools that navigate pages, click elements, fill forms, and extract content using selectors. Runs entirely on text snapshots of page structure, making it faster and more reliable than screenshot-based alternatives. Useful when you need an AI agent to scrape data, test web apps, or automate multi-step browser tasks. Works with any MCP client and installs via npx, so no separate browser setup required.