The request names Playwright, so Playwright comes first: it is an end-to-end testing and browser automation framework with an SDK and a token-efficient CLI for coding agents 1. Alternatives that do browser automation for agents are the Browser Use cloud browser 6, Browserless cloud browser with Playwright connection 10, and agent-browser CLI 7.
- 1
Playwrightplaywright.devwebsite read, tools not yet checked
Runs end-to-end tests and browser automation across Chromium, Firefox and WebKit, with auto-waiting assertions, and offers a Playwright CLI for coding agents 1.
official:SDK · playwright+232 community tools built for it
- 2
Browser Usebrowser-use.comverified and signed
Gives an AI agent direct browser control via CDP or a cloud browser for web automation, scraping and testing 6.
official:MCP server · com.browser-use/browser-use
for agents: browser-use · cloud · browser-use
- 3
Browserlessbrowserless.ioverified and signed
Provides a cloud browser that agents connect to over MCP, Puppeteer or Playwright, with stealth and authenticated profiles 10.
+2 community tools built for it
for agents: run_function · run_bql_query · browserless_function
- 4
agent-browseragent-browser.devwebsite read, tools not yet checked
A browser automation CLI for AI agents with compact text output and ref-based element selection 7.
Sources
- 1Fast and reliable end-to-end testing for modern web apps | Playwrightplaywright.dev · read 2026-10-29
- 6Browser Use Agents & Browser Infrastructure | Browser Usebrowser-use.com · read 2026-10-29
- 7agent-browser | Browser Automation for AIagent-browser.dev · read 2026-10-29
- 10The Browser Your AI Agents Run On | Browserlessbrowserless.io · read 2026-10-29
For agents: the 10 actions behind this answer
· Playwright website read, tools not yet checked
Web automation and testing for apps, scripts, and AI agents
· PlaywrightGen website read, tools not yet checked
Playwright tests written from your real page, run in a real browser and fixed until they pass — then reviewed by your team, with every approval and result on record.
playwright-browser-automation · playwright-browser-automation verified and signed
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser i
run-smoke-tests · run-smoke-tests verified and signed
Run Playwright smoke tests, debug failures, and verify fixes
firecrawl_interact · Firecrawl MCP Server verified and signed
Open or reuse a live browser session to navigate a page, click controls, fill fields, or run browser code. Provide either `url` or `scrapeId`, and either a natural-language `prompt` or executable `code`; code can run as Bash, Python, or Node with a bounded timeout. This acts on the live site, so act
browser-use · browser-use verified and signed
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(use_cloud=True)), Playwright, Puppeteer or any CDP client.
· agent-browser website read, tools not yet checked
Browser automation CLI for AI agents
· Qiksy Bridge website read, tools not yet checked
Give your AI agent the Chrome tab you already have open: your session, your logins, the page you are looking at. MCP bridge for Claude Code, Cursor, Codex and VS Code. Without an agent it still fills forms and catches console, network and accessibility errors while you click.
tailwind-best-practices · tailwind-best-practices verified and signed
Tailwind CSS styling guidelines for Mastra Playground UI. This skill should be used when writing, reviewing, or refactoring styling code in packages/playground-ui and packages/playground to ensure design system consistency. Triggers on tasks involving Tailwind classes, component styling, or design t
run_function · Browserless (Activepieces) verified and signed
Run Puppeteer Function — Run your own Puppeteer code in a Browserless browser and return what it returns.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.