Task · Browser & Computer Use
Best AI agents to test web applications
This task needs 2 capabilities. 4 tools cover all of them; 438 cover at least one.
| # | Tool | Coverage | Access | Trust | Seen |
|---|---|---|---|---|---|
| 1 | playwright-wizard-mcpMCP MCP server providing Playwright test generation wizard with intelligent prompts and best practices | 100% | REMOTELOCAL | DECLARED | 4d ago |
| 2 | claudetestMCP Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs. | 100% | REMOTELOCAL | DECLARED | 4d ago |
| 3 | smolanalyticsMCP End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free. | 100% | REMOTELOCAL | DECLARED | 4d ago |
| 4 | QlaneMCP AI QA that runs your app in a browser on every pull request: projects, test targets, test cases. | 100% | REMOTELOCAL | DECLARED | 4d ago |
| 5 | Oya BrowserMCP Real Chrome for agents: start a browser, read pages as numbered markdown, click, type, hand off. | 50% | REMOTELOCAL | DECLARED | 22m ago |
| 6 | Hronaut Browser MCPMCP Control visible, persistent Hronaut browser workspaces through a local MCP connection. | 50% | REMOTELOCAL | DECLARED | 37m ago |
| 7 | ghostlightMCP Visible local browser automation in signed-in Chromium, with optional policy and audit. | 50% | REMOTELOCAL | DECLARED | 2h ago |
| 8 | Puptra PDF SnapshotMCP One-call URL-to-PDF and full-page screenshot API with Puppeteer's page.pdf()/page.screenshot()... | 50% | REMOTELOCAL | DECLARED | 4h ago |
| 9 | Behavior Runtime MCPMCP In-browser ~60Hz behavior tree execution engine with reactive triggers and safety guardrails. | 50% | REMOTELOCAL | DECLARED | 4h ago |
| 10 | Aether WCAG ScannerMCP WCAG 2.1 AA accessibility scanner (Playwright + axe-core) with grounded, browser-verified fixes. | 50% | REMOTELOCAL | DECLARED | 5h ago |
| 11 | DrobekMCP Build, preview, version and publish small browser apps from coding agents over MCP. | 50% | REMOTELOCAL | DECLARED | 6h ago |
| 12 | humMCP Free music for your coding agent. Play songs, mood stations and Spotify links in your browser. | 50% | REMOTELOCAL | DECLARED | 6h ago |
| 13 | invisible_playwright_mcpMCP AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions. | 50% | REMOTELOCAL | DECLARED | 7h ago |
| 14 | H/Ai BrowserMCP Let AI agents drive VS Code's built-in browser alongside you, with click-to-source. | 50% | REMOTELOCAL | DECLARED | 7h ago |
| 15 | cmssyMCP Headless CMS whose page sections are defined by your own code: pages, records, media, commerce. | 50% | REMOTELOCAL | DECLARED | 8h ago |
| 16 | Testiny Test ManagementMCP An MCP server that provides access to Testiny projects, test cases and test runs | 50% | REMOTELOCAL | DECLARED | 15h ago |
| 17 | zenrows-mcpMCP Zenrows MCP server — Fetch, Extract, Batch, and Browser Sessions for AI coding assistants | 50% | REMOTELOCAL | DECLARED | 15h ago |
| 18 | safari-mcpMCP Native Safari browser automation for AI agents — 98 tools, zero Chrome overhead. | 50% | REMOTELOCAL | DECLARED | 16h ago |
| 19 | promoshotMCP Headless MCP: author and render PromoShot .promo video projects (stills, GIFs, video). | 50% | REMOTELOCAL | DECLARED | 19h ago |
| 20 | SeleniumBase MCPMCP Stealthy browser automation, testing, and web-scraping via CDP Mode. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 21 | notion-mcp-serverMCP Token-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 22 | Screen BrowserMCP Narrated demo and tutorial videos of your web app, from a guide or your coding agent. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 23 | BCD — Bridge Control DelegateMCP Use your own Mac from ChatGPT, Claude or Codex: files, commands, documents, and a browser. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 24 | periscopeMCP A real Safari-engine (WebKit) browser for agents on macOS: sessions, extraction, bot checks. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 25 | ProofhandMCP Human QA on real phones and browsers for your coding agent. Pass/fail per step, with screenshots. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 26 | Aginx BrowserMCP Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 27 | Delhaize receiptsMCP Fetch your own Delhaize (Belgium) till receipts and weekly promotions with a headless browser. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 28 | ParallelSandboxMCP Remote Linux boxes for coding agents: Docker, a browser, screenshots, logs, human takeover. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 29 | BrowsenticMCP Hands your real, logged-in browser to your agent: an AI side panel extension, also over MCP. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 30 | EaselMCP A headless painting engine for AI agents: brushes, paint load, wet blending, canvas texture. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 31 | NativePortMCP 30+ web-access and AI APIs behind one key: search, scraping, browsers, voice, OCR and LLMs. | 50% | REMOTELOCAL | DECLARED | 1d ago |
| 32 | acrawlMCP Autonomous web crawler. 17 browser tools + goal-driven run_goal agent. Single binary, stealth. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 33 | mcpMCP Build, run, inspect, and publish browser extensions from any MCP client. 30 tools, 11 browsers. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 34 | UXMachineMCP Measures your site in a real browser and returns verifiable observations, with evidence and limits. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 35 | browser-compat-mcp-serverMCP Browser compatibility and Baseline status for any web feature — offline, from bundled MDN data. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 36 | QuickPeekMCP Turn a URL into a narrated demo video: real browser walkthrough, AI voiceover, captions burned in. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 37 | klyo games: publish HTML5 browser gamesMCP Publish HTML5 browser games from your AI assistant: own address, live stats, 70% ad share. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 38 | three.ws HeraldMCP Tell your human in person: a 3D character walks onto their open browser tab and says it out loud. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 39 | browser-buddyMCP Let AI coding agents read pages through your real, logged-in Chrome browser. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 40 | KeyShot MCPMCP Control local KeyShot scenes, cameras, environments, and renders through headless scripting. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 41 | oassis — web scraping, crawling and browser control for AI agentsMCP Scrape to markdown, map and crawl sites, drive a real browser. Pay per call, no API key, no signup. | 50% | REMOTELOCAL | DECLARED | 2d ago |
| 42 | shaft-mcpMCP SHAFT browser automation, capture, and offline deterministic failure diagnosis | 50% | REMOTELOCAL | DECLARED | 3d ago |
| 43 | Magic CloudMCP Generate secured CRUD APIs over your database, run SQL, manage files, tasks and a headless browser | 50% | REMOTELOCAL | DECLARED | 3d ago |
| 44 | DEEPBOMMCP Browser-local and CLI static evidence for deployed AI model artifacts. | 50% | REMOTELOCAL | DECLARED | 3d ago |
| 45 | GrabbitMCP Screenshot any URL as a hosted image. No local browser; handles bot walls and full-page captures. | 50% | REMOTELOCAL | DECLARED | 3d ago |
| 46 | ConnectionsMCP AWS, GitHub and connected services from your agent, no keys to paste, plus local shell and browser. | 50% | REMOTELOCAL | DECLARED | 3d ago |
| 47 | cdpilotMCP Zero-dependency browser automation over raw CDP — no Puppeteer, Playwright, or Selenium. | 50% | REMOTELOCAL | DECLARED | 4d ago |
| 48 | ShiplightMCP An MCP server that provides browser automation | 50% | REMOTELOCAL | DECLARED | 4d ago |
| 49 | MyClawn DesktopMCP Hand jobs to an always-on cloud desktop with a real browser, saved logins and its own email. | 50% | REMOTELOCAL | DECLARED | 4d ago |
| 50 | webrecipeMCP Save how to read a public web page once, then fetch fresh items as JSON without a browser. | 50% | REMOTELOCAL | DECLARED | 4d ago |
Page 1 / 9Next →
Coverage = share of this task's required capabilities that an agent or tool documents. For AI agents, capabilities are those stated on the vendor's website; for tools, they are matched automatically from the publisher's description (keyword method, low confidence).