For web QA exploration, the strongest fits are Browser Use, which ships a QA action returning a quality score with evidence 919, and Shiplight, which offers MCP-based browser QA testing 616. Browserbase 1 and Playwright 2 provide the browser control layer that exploratory QA runs on, and Test-Lab.ai 8 runs AI agents that click through apps like real users.
- 1
Browser Usebrowser-use.comverified and signed
Gives an AI agent a real browser and includes a QA action that tests a website or web app and returns a 1-5 quality score with evidence 19.
official:MCP server · com.browser-use/browser-use
for agents: qa · browser-use · browser
- 2
Shiplight AI Docsshiplight.aiverified and signed
Autonomous AI agents for QA testing with MCP browser automation, YAML end-to-end tests and cloud execution 6; its verify action checks UI changes in the browser 16.
official:MCP server · Shiplightpackage · Shiplight+1 community tools built for it
for agents: shiplight · verify · cloud
- 3
Browserbasebrowserbase.comverified and signed
Browser infrastructure for agents that handles login, flows and dynamic content, with an MCP server and a browser skill for natural-language browsing 111.
official:MCP server · @browserbasehq/mcpskill · browserskill · agent-experienceskill · autobrowseskill · browser-to-api+9 community tools built for it
for agents: autobrowse · browser · browser-trace
- 4
Playwrightplaywright.devwebsite read, tools not yet checked
End-to-end testing framework with auto-waiting and tracing across Chromium, Firefox and WebKit, plus a CLI for coding agents 2.
official:SDK · playwright+230 community tools built for it
- 5
Test-Lab.aitest-lab.aiwebsite read, tools not yet checked
AI agents that click, scroll and navigate a web app like real users to find bugs and broken flows without test scripts 8.
Sources
- 1Browserbasebrowserbase.com · read 2026-10-29
- 2Fast and reliable end-to-end testing for modern web apps | Playwrightplaywright.dev · read 2026-10-29
- 6Shiplight AI Docs — Autonomous QA Testing with MCP & YAML | %sdocs.shiplight.ai · read 2026-10-29
- 8AI Testing That Works Like Real Users | Test-Lab.aitest-lab.ai · read 2026-10-29
- 9Browser Use Agents & Browser Infrastructure | Browser Usebrowser-use.com · read 2026-10-29
- 11autobrowse: declares "autobrowse" (the record we read and signed)unfragile.ai · read 2026-10-24
- 16shiplight: declares "shiplight" (the record we read and signed)unfragile.ai · read 2026-10-24
- 19qa: declares "qa" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
autobrowse · autobrowse verified and signed
Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser auto
· Playwright website read, tools not yet checked
Web automation and testing for apps, scripts, and AI agents
automation · WebDriver Support verified and signed
web-browser · web-browser verified and signed
Automate and interact with web pages through Chrome or Chromium using the Chrome DevTools Protocol (CDP): navigate, click, fill forms, inspect content, take screenshots, and debug console or network activity. Use when an agent needs a real browser. Prefer headless Chrome unless visible browser inter
audit-website · audit-website verified and signed
Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, technical, content, accessibility, and 16 other rule categories (300+ rules), returns an LLM-optimized report, then drives an iterative fix loop, mapping issues to source files, applying fixes, a
shiplight · shiplight verified and signed
Shiplight QA toolkit — the single entry point for all Shiplight test/QA work. Use ONLY when the user explicitly says 'shiplight' (e.g. 'write a shiplight test', 'use shiplight to verify X', 'shiplight cover') or invokes /shiplight. Routes to subcommands: init, setup-test-auth, update, create-yaml-te
tavily_crawl · Tavily verified and signed
Crawl a website starting from a URL. Extracts content from pages with configurable depth and breadth.
· Test-Lab.ai website read, tools not yet checked
Test your web app with AI agents that click, scroll, and navigate like real users. Find bugs, broken flows, and UI issues in minutes - no scripts needed.
qa · qa verified and signed
QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence. Use when the user wants to test, QA, evaluate, score, or "check how good" a site, page, flow, or app — including a local dev server (e.g. "qa test localhost:5173", "does the checkout work?", "rate t
· Codecomber website read, tools not yet checked
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.