io.github.aethynio/aethyn-browser-mcp
io.github.aethynio/aethyn-browser-mcp
Local Playwright browser through residential proxies — agent picks country + sticky identity
OLACHEAP · MCP WORKSPACE / BROWSER
Browser MCP servers can inspect pages and interact with forms. Read-only screenshots, navigation, sign-in, purchase, and destructive account actions have very different safety requirements.
Results come from the current synchronized Registry snapshot, not popularity or activity.
io.github.aethynio/aethyn-browser-mcp
Local Playwright browser through residential proxies — agent picks country + sticky identity
io.github.allchemylabs/aether-wcag-scanner
WCAG 2.1 AA accessibility scanner (Playwright + axe-core) with grounded, browser-verified fixes.
io.github.aybelatchane/mcp-server-terminal
MCP server for AI agents to interact with terminal applications. Think Playwright for terminals.
io.github.beycom/onetool-mcp
One MCP for devs incl Brave,Google,Tavily,Context7,AWS,Excalidraw,DB,GitHub,DevTools,Playwright
io.github.com55/pyside6-mcp
Playwright-style MCP to inspect, control, and debug PySide6 desktop GUIs.
io.github.devinwang/cloak-browser-mcp
Playwright-compatible MCP server on CloakBrowser stealth Chromium: 86 tools, humanized input.
io.github.dinesh-nalla-se/playwright-mcp
Playwright Tools for MCP
io.github.dpozimski/pdfspark-mcp
Convert HTML or URLs to PDF documents powered by Playwright
io.github.eyrockscript/test-card-hub
Sandbox test cards, Playwright tests, real-card scanner and decline codes for LATAM gateways.
io.github.fasteningcode/claudetest
Playwright & Appium test automation for Claude. Generate tests, diagnose failures, open fix PRs.
io.github.feder-cr/invisible-playwright-mcp
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
io.github.gAI-ventures/pilotfish
Browser automation MCP: a real Chrome for any AI agent, 72% fewer tokens than Playwright MCP. Free.
io.github.hubertgajewski/playwright-report-mcp
Run Playwright tests and surface structured results for AI agents doing test failure analysis.
io.github.inSideos-designs/cowork-qa
Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.
io.github.katatan-org/katatan-TEST
KATATAN E2E testing agent set — Playwright + KATATAN MCP integration
io.github.masakaai/rea-captcha
Safe same-session CAPTCHA handoff and fresh-evidence resume for Browser Use and Playwright agents.
io.github.mechreaper007x/clipacanvas
Render HTML, CSS, SVG, and Canvas animations to MP4 locally via Playwright/Chromium and FFmpeg.
io.github.mehmetnadir/cdpilot
Zero-npm-dependency browser automation over raw CDP — no Puppeteer, Playwright, or Selenium.
io.github.microsoft/playwright-mcp
Playwright Tools for MCP
io.github.noncelogic/mcp
Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.
io.github.oguzc/playwright-wizard-mcp
MCP server providing Playwright test generation wizard with intelligent prompts and best practices
io.github.perzianhq/mantis
The web as short, numbered text for AI agents: a lean browser interface over Playwright.
io.github.qualienai/qualien-mcp
MCP gateway for QA/SDET work: Playwright, files, GitHub, Jira, Postgres & more in one connection.
io.github.restspace/sitelooper
Record a browser flow once with a model, then compile it to a Playwright spec that needs no model.
Synchronized data; no invented downloads, reviews or ratings.
OLACHEAP · PRACTICAL GUIDES
Start with a public page and test navigation, text extraction, and a screenshot. Confirm the domain and final URL after redirects before trying any authenticated workflow.
Check browser isolation, session storage, whether credentials are visible to tools, handling of downloads, and whether form submission requires user confirmation. Separate production accounts from testing sessions.
Web pages can display convincing fake controls or prompt-injection text. A click that looks harmless may trigger a transaction; require an explicit confirmation step before checkout, publishing, or sending messages.
Use their exact Registry IDs to compare published connection information before granting permissions.