"Playwright" matching MCP servers:

Enables AI agents to control a web browser using Playwright, supporting navigation, interaction, and data extraction through natural language.

Enables LLMs to autonomously navigate, type, click, and extract data from web pages using Playwright, without hardcoded selectors.

A server that enables LLMs to interact with web pages through structured accessibility snapshots without needing screenshots or visually-tuned models.

A stealth Firefox browser exposed as an MCP server that lets AI agents browse and interact with real websites without being blocked by anti-bot systems.

Enables AI agents to run, debug, and inspect Playwright end-to-end tests, returning structured pass/fail stats, failure diagnostics with actionable fix hints, live DOM inspection, selector validation, visual diffs, and flakiness verdicts instead of raw test output.

Playwright browser automation tuned for single-page apps (React/Vue/Angular) — screenshots, form filling, action chains, persistent sessions and 140+ device presets.

A tab-aware Playwright MCP server that enables multiple agents to operate on different tabs concurrently while sharing a single browser context and login session.

An MCP server that provides a stealth-enhanced Playwright browser automation engine with anti-detection features, enabling AI agents to navigate websites, interact with elements, and bypass anti-bot systems.

Enables AI assistants to control web browsers through Playwright automation, providing 50+ tools for navigation, interaction, testing, accessibility audits, and visual testing across Chromium, Firefox, and WebKit.

Enables AI agents to perform one-shot triage of Playwright trace files, pinpointing root causes like backend API failures or locator issues and generating self-healing code fixes in a single low-token call.

Turns text prompts into premium iOS UI mockups (PNG + HTML). Powered by Claude + a Playwright headless renderer. Two backends: local claude CLI (uses your Claude Code subscription) or the Anthropic API.

An MCP server that automates filling out BLok Berichtsheft (training reports) via browser automation using Playwright.

Records narrated walkthroughs of any webapp by orchestrating Playwright, speech-mcp TTS, and FFmpeg composition.

An MCP server for Excalidraw diagram creation and headless rendering, enabling interactive canvas editing and automated SVG/PNG export via Playwright.

Read-only Playwright CI results for coding agents: tells whether a failing test is new in this PR, already failing on main, or known flaky, with per-test history.

MCP server for web scraping with natural language, enabling site crawling, page fetching, and extraction of emails, phones, links, and social profiles. Returns clean markdown, handles JavaScript rendering, and respects rate limits.

Actualiza tu hoja de vida de CvLAC (MinCiencias) conversando con tu asistente de IA, sin llenar formularios a mano. Lee, agrega, corrige y borra formación, experiencia, proyectos, artículos, libros, software, eventos y perfil. Pregunta antes de borrar o de crear algo parecido a lo que ya existe. Corre en tu computador con Playwright: tus credenciales no salen de él. Proyecto no oficial.

A licensed, locally run Playwright E2E testing MCP server for Claude Desktop and Cursor. It lets AI coding agents inspect semantic accessibility structure, validate role-based browser flows with explicit assertions, and generate reusable Playwright tests.

Self-healing browser automation MCP server integrating Playwright with LLM-assisted locator repair.

Turn screen recordings into automated Playwright E2E reproduction tests, structured GitHub bug reports with clickable video timestamps, and SOP walkthroughs.