Best Playwright AI Skills & MCP Servers

MCP server for Lastest visual regression testing platform — lets AI agents run tests, review diffs, and manage baselines

QA STLC Agents — six MCP servers + skills for AI-powered test case, Gherkin, self-healing Playwright generation, Helix-QA file writing, and existing-framework migration against Azure DevOps and Jira Cloud. Includes an 8-strategy LocatorHealer with a live

Code-aware browser testing agent — reads your codebase, understands functionality, tests every element, reports with screenshots. Works as MCP server for Cursor/Claude Code or standalone CLI.

MCP-first browser primitives for AI agents — real eyes and hands on the web. Local-first. Vendor-agnostic. Yours to own.

The web data platform for AI agents — fetch, search, crawl, extract, monitor, screenshot. 55+ domain extractors, 65-98% token savings, MCP server included. One API call.

MCP Server for Real Browser - Patchright (undetected Playwright fork) with Stealth Mode, Ad Blocker, and Turnstile Auto-Solver for undetectable web automation.

Convert Playwright scripts into Tap v2 plans. Compile .spec.ts / .test.ts files into deterministic v2 Plan JSON that runs at zero LLM tokens in Claude Code, Cursor, and any MCP host.

Screen-reader navigation cost analyzer. Measures how hard it is for AT users to discover, reach, and operate web content.

Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg

Drive any Electron app from your AI. MCP server with 93 tools, 4 recipe packages (Slack/Discord/Notion/Linear), security primitives, and a CLI mirror. The testing surface area Tauri structurally cannot match.

Xiaohongshu (rednote / 小红书) MCP server for Claude Desktop, Cursor and AI agents — search, read, comment, like and publish notes via npx. Node.js + Playwright port of xiaohongshu-mcp.

MCP server that lets AI read Notion, Google Docs, Jira & any login-protected page via a real browser

Currents MCP server

A Model Context Protocol (MCP) server for performing automated accessibility scans of web pages using Playwright and Axe-core

MCP server for Google search via warm Chrome profile. No API key.

Playwright-based testing and evaluation framework for MCP servers

SkillFM local — single npm package for the SkillFM platform on user nodes. Subcommand router exposes (1) Beacon MCP stdio server (cost-optimizer for any agent; merged in from @skillfm/beacon-mcp on 2026-05-01), (2) skill runtime (BYOK Playwright / brain r

JD Codec — local MCP proxy that compresses browser-agent snapshots ~80%+ via a cloud codec, with on-device PII redaction. The privacy-first connector for Playwright MCP and any MCP-capable agent.

MCP server for running Playwright tests and reading structured results — designed for AI agents doing test failure analysis

MCP server for browser automation using Playwright with profile management, page registry, and multi-browser support

MIT-licensed MCP bridge to the Alethia runtime — the patent-pending zero-IPC E2E test runtime for AI agents. 2-5x faster than Playwright MCP. Signed evidence packs, EA1 fail-closed safety gate, WCAG + NIST 800-53 audits built in. Local-first, zero telemet

Secure MCP server for web browsing with multi-layer fetcher chain - no API keys required

NIA AI Web Evaluation Agent MCP Server - Autonomous browser testing and debugging

Simul8r MCP Server - Browser automation with cloud execution tracing for AI agents