Playwright MCP
Featuredby Microsoft
Official Microsoft MCP server for browser automation. Agents navigate pages and interact with elements via accessibility snapshots — no vision model required.
Skills
Accessibility Snapshots
Generates structured accessibility trees of any page so agents navigate without screenshots
Page Navigation
Navigate URLs, follow links, go back/forward, and control browser history programmatically
Element Interaction
Click, type, focus, hover, and select elements using stable accessibility selectors
Form Automation
Fill and submit forms, handle dropdowns, checkboxes, and file uploads without vision
Network Monitoring
Inspect network requests and responses during agent-driven browser sessions
Related Agents
Browser Harness
Connects an LLM directly to a real Chrome browser over a single CDP websocket, letting the agent write the helper code…
Browser Use
Open-source Python library for AI browser automation. Control any website with natural language; cloud adds stealth bro…
BrowserOS
Drives a local open-source Chromium using your existing logged-in sessions, feeding external agents compact page snapsh…
Crawl4AI
Crawls and scrapes web pages into clean Markdown for RAG pipelines, with CSS, XPath, and LLM-driven structured extracti…