browser-mcp vs playwright-mcp
browser-mcp: Browser MCP enables AI agents like Claude Code to control a user's real Chrome browser, leveraging existing logins, cookies, and 2FA to operate on sites where traditional headless browsers fail. It offers advanced capabilities like multi-session management, human-in-the-loop interaction for sensitive steps, and built-in tools for complex web interactions and CAPTCHA solving.; playwright-mcp: Playwright MCP is a server that leverages Playwright's browser automation capabilities to enable Large Language Models (LLMs) to interact with web pages. It utilizes structured accessibility snapshots, allowing LLMs to process web content without relying on visual input or traditional screenshots.
TL;DR
Automate operations on platforms with no public API (e.g., legacy systems, social media).
- You want an agent to drive a real browser through structured accessibility snapshots instead of screenshots, so no vision model is needed.
- You need Firefox, WebKit or Edge as well as Chrome: the README's --browser option lists chrome, firefox, webkit and msedge.
- You want to test or script flows with isolated in-memory profiles (--isolated), device emulation (--device) or saved Playwright traces (--save-trace).
- Your main goal is debugging or performance analysis of a page; Chrome DevTools MCP exposes performance traces and network inspection as dedicated tools.
- You need proxies, CAPTCHA handling or large-scale scraping of protected sites; that is outside what the README claims for this server.
- You want to treat it as a sandbox: the project says its origin allow and block lists are not a security boundary.
Side-by-Side Comparison
Features
Use Cases
Best For
FAQ
Deploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.