도구

Lets agents drive a real browser through the accessibility tree: navigate, click, fill forms and take screenshots, without needing a vision model. Maintained by Microsoft.

Drives local web apps with Python Playwright scripts to verify features, debug the UI, take screenshots and read browser logs. Includes helper scripts to start and stop dev servers. Official Anthropic skill.

After code changes, has the agent check routes, errors and page behavior in the running Next.js app via /_next/mcp and agent-browser to confirm the change really works. Maintained by Next.js; needs Next.js 16.3+ (Turbopack) and agent-browser.

Drives a Next.js route to instant navigation under Cache Components: writes a failing @next/playwright instant() e2e test, pushes Suspense boundaries down to grow the static shell until it passes, and keeps the test as a regression guard. Requires Next.js 16.3+ with cacheComponents.

Microsoft's cross-browser end-to-end testing framework: one API drives Chromium, Firefox and WebKit, npx playwright test runs tests in parallel and isolation, with auto-waiting and trace replay for debugging failures.

Companion skill for the agent-browser CLI: has the agent load usage matching the installed version to navigate, fill forms, take screenshots and run exploratory tests, and can also drive Electron desktop apps. Install the agent-browser CLI first; from Vercel Labs.

Browser automation CLI built for AI agents in native Rust: open pages, click and fill forms by refs from accessibility tree snapshots, read text and take screenshots, with compact snapshots and output limits to save context. From Vercel Labs; reuses local Chrome or installs one.

Browser automation plugin from Vercel Labs: agents drive Chrome through accessibility tree snapshots and element refs to navigate, click, fill forms and take screenshots, for web testing and exploratory QA. Install the agent-browser CLI first (npm, Homebrew or Cargo).

Accessibility review plugin with an audit command, a UI validation subagent, and WCAG 2.2 and screen reader testing skills. Before design reviews or launch, the agent checks contrast, keyboard use and screen reader support and suggests fixes. For Claude Code; automated checks need Node.js.

Wraps Microsoft's Playwright MCP so agents can drive a real browser to navigate, click, fill forms and take screenshots for end-to-end tests and page checks. In Anthropic's official marketplace; needs Node.js.

MCP built into the CLI of the Maestro mobile UI testing framework (maestro mcp): lets agents view the screen, tap, scroll and assert on iOS/Android simulators, Android devices or Chromium, and write and run YAML end-to-end flows. Needs the Maestro CLI and Java 17+. Official.

Microsoft Playwright's official browser CLI for coding agents: open pages, click and type, take screenshots and manage sessions, and install the companion skills in one step. Uses fewer tokens than Playwright MCP. Needs Node.js 18+.

Companion skill for the official Playwright CLI: short commands to open pages, click and fill forms, take snapshots and screenshots, and write and debug Playwright tests, using less context than the MCP approach. Maintained by Microsoft; needs Node.js.

OpenAI's official Codex plugin for building frontend apps and generating visual assets, testing and debugging in a browser, plus best-practice skills for React, shadcn/ui, Stripe payments and Supabase databases. Codex only.

Tests and debugs a locally running frontend with Codex's Browser plugin or Playwright: checks blank pages, framework and console errors, captures screenshots, re-verifies after fixes and writes a QA report. Maintained by OpenAI; formerly playwright-interactive in openai/skills.

Lets coding agents control real Chrome with short Puppeteer scripts, with named pages that keep state across calls, accessibility-tree snapshots and screenshots for self-testing web changes. Install the dev-browser CLI globally first; macOS and glibc Linux only.

Community Playwright browser automation MCP from ExecuteAutomation (not Microsoft's official one): navigate, click, fill forms, screenshot and scrape page text, plus send HTTP requests, assert network responses and record actions into test code, with 143 device emulations built in.

Lets agents write and run Playwright scripts on the fly for browser testing and automation, auto-detecting local dev servers, with screenshots, responsive checks, login flows and link checking. After installing, run npm run setup in the skill directory.

Lets agents write and run Playwright scripts on the fly for browser automation: page tests, UX checks and multi-step flows, opening a visible browser by default and auto-detecting local dev servers. After installing the plugin, run npm run setup in the skill directory.

Testing practices for Vue apps: Vitest and Vue Test Utils, black-box component tests, flushPromises for async code, helpers for testing composables, Pinia stores, async components and Teleport, avoiding snapshot-only tests, and Playwright for end-to-end testing.

Browser automation MCP built on Selenium WebDriver for Chrome, Firefox, Edge and Safari: locate elements, click and type, upload files, take screenshots, run scripts, and handle alerts and cookies. A good fit for test teams already using Selenium.

Official testing skills from TestMu AI (formerly LambdaTest) covering 40+ frameworks including Selenium, Playwright, Cypress, Appium, pytest and JUnit, guiding agents to write unit, end-to-end and mobile tests. Runs locally; cloud cross-browser and real-device runs need an account.

Cross-platform UI automation skills built on Midscene.js visual recognition: control browsers, desktops, Android, iOS and HarmonyOS devices in natural language, and set up Vitest + Midscene E2E tests. Bring your own vision model API key; maintained by the Midscene team.

Browser Use's official plugin: connects the Browser Use MCP so Claude can drive your local Chrome or a cloud browser to browse, extract data, fill forms, test sites and take screenshots. Needs uv; cloud browsers need sign-in or an API key.