playwright
81 servers · 2,522★ total
Open-source self-improving QA agent for software teams. A test harness with memory. Write tests in natural language for web and mobile. agent-qa learns from every run, adapts to UI changes, and catches regressions before you ship.
Google search MCP. One MCP replaces search + fetch + academic-paper extractor.
Model Context Protocol server that integrates AgentQL's data extraction capabilities.
A unified web extraction and stateful automation engine for AI. Replaces heavy testing frameworks with token-optimized browser control, deep research, and HITL.
1,486 real web design systems, extracted into machine-readable specs. An MCP server for AI coding agents — so what they build has taste, not just working code.
Model Context Protocol server for Playwright with Chrome DevTools Protocol support
From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.
This project demonstrates how to use AWS Bedrock with Anthropic Claude and Amazon Nova models to create a web automation assistant with tool use, human-in-the-loop interaction, and vision capabilities.
Local-first, no-API-key MCP server for web search, fetch, and document reading. Multi-engine (DuckDuckGo, Mojeek, Startpage), smart Playwright fallback, FTS5 cache, LLM-tuned output.
⚡ CloakBrowser MCP server for AI agents: Playwright-powered browsing, clean tool forwarding, Docker support, and multi-session HTTP transport.
An MCP server for parallel browser automation by AI agents with multiple cloud providers
A Model Context Protocol (MCP) integration that provides Claude Desktop with autonomous browser automation capabilities. This agent enables Claude to interact with web content, manipulate DOM elements, execute JavaScript, and perform API requests.
Record any browser page as GIF or video via MCP — powered by Playwright + ffmpeg
AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/Android/BlueStacks).
First open-source OpenEvidence MCP server: browser-session medical research tools for Codex, Claude Code, and MCP clients
A minimal Model Context Protocol 🖥️ server/client🧑💻with OpenAI and 🌐 web browser control via Playwright.
Intelligent stealth browser MCP server for AI agents with 30 tools, 22 anti fingerprint scripts, and LLM powered extraction. Works seamlessly with Cursor, Claude, VS Code, and any OpenAI compatible LLM.
Bridge local MCP clients to browser WebMCP tools through Playwright, using native WebMCP when available and injected adapters when not.
Self-hostable, MCP-native testing platform. Manual test management, deterministic runs, optional AI. Your stack, your LLM, your data.
Lightweight stealth-oriented browser MCP server in Rust — one shared Chrome for many AI agents, 64+ Playwright-style tools, no Node.js runtime.
MCP server for browser automation via Patchright. Multi-profile Chromium, headed/headless, StreamableHTTP protocol. Includes dashboard, skills, and AI agent setup.
Fly the web on a string — a lightweight (~7MB) Rust browser-automation MCP server for AI agents. Streamable HTTP, 21 tools, HTML→PDF, plus a Puppeteer-compatible npm facade.
MCP server for stealth browser automation via Camoufox — 79 tools, npx install, anti-bot stealth
Go library, CLI, and MCP server for Camoufox browser automation.
Lastest Visual Regression Testing - Cloud/Self-hosted version
AI-powered MCP proxy for Playwright and Figma. Optimize Claude Code and AI agents with session recovery, context reduction and intelligent tool routing.
Open-source browser automation broker for AI agents: persistent Chrome profiles, proxy-aware identities, remote API, MCP tools, browser-use/OpenBrowser adapters, human auth handoff, telemetry, and audits.
A Chrome browser shared in real time between you and Claude Code (CDP + Playwright MCP): you clear the captchas/logins, Claude operates and learns each site's navigation. Frugal, per-site memory.
MCP server that drives Google Flow (Veo / Nano Banana) through its internal tRPC API, with a hard credit-cost gate
acrawl — LLM-powered web crawler. Describe what you want in plain English, get structured data back. Single Rust binary, 25 providers, MCP server built-in.
8-armed SEO intelligence - MCP server + CLI with 23 tools for rank tracking, Google Analytics, site auditing, keyword research, competitive analysis, and performance monitoring
Playwright MCP Server 一个基于 FastMCP 框架的专业级 Playwright 浏览器自动化 MCP 服务器，为 LLM 应用提供强大的网页交互和数据提取能力。
Humanize browser automation for AI agents, QA tests, and demos. Playwright-first — record sessions to video or runnable tests, and drive it over MCP from your favorite AI.
Monorepo for SAP MCP servers (API Hub, Road Map Explorer, SAP Notes) and their shared SAP authentication module — npm workspaces.
LinkedIn for AI assistants (MCP) — profiles, people/job/company search, feed & messaging as structured JSON, plus gated writes (connect/message/post/react/comment) via LinkedIn's API instead of DOM-clicking. Stealth-browser engine, 22 tools, built-in safety layer. Claude · Cursor · any MCP client.
Turn any website into an MCP server. Auto-generates WebMCP tools from live pages - no site cooperation needed.
Give any AI a real computer. Open source MCP server with Ubuntu sandbox, browser automation, desktop control, and 30+ tools. Works with Claude Code, Cursor, Claude Desktop.
MCP server for RedNote (Xiaohongshu) — analyze content, comments, and trends with structured tools for LLM workflows.
Seamless Claude Code ↔ Playwright integration with intelligent caching. Transform browser automation with AI-aware selector resolution and persistent sessions.
A Model Context Protocol (MCP) server that provides web development tools for AI assistants. Enables browser automation, DOM inspection, network monitoring, and console analysis through Playwright.
CNKI(中国知网)文献检索·PDF下载·Zotero自动导入关联 MCP 服务器 | MCP server for CNKI literature search, PDF download, and Zotero import
Multi-tenant X (Twitter) automation platform for AI agents — drive X via MCP or REST with browser-backed sessions, not the public API.
MCP server providing Playwright test generation wizard with intelligent prompts and best practices
Two OSS products on one rrweb substrate: tracelane (self-contained HTML test-failure replays for WDIO/Playwright/Cypress) + peek (local-first browser-session forensics + repro for AI coding agents, over MCP). No SaaS, no telemetry, local-first.
Validate AI-built front-ends against their Figma design — deterministic token + geometry conformance, not pixels. MCP server + Claude Code skill.
By leveraging Playwright under the hood, this server seamlessly injects into the OpenCut browser environment, granting LLMs programmatic access to manipulate the timeline, scenes, media assets, rendering engine, and more...
MCP server para el CENDOJ 🇪🇸 — Acceso automatizado a resoluciones judiciales de España, filtros avanzados de jurisprudencia y lectura de sentencias mediante Model Context Protocol y API REST
MCP server for AI-assisted tax filing through FreeTaxUSA using Playwright browser automation
Multi-session browser MCP for AI agents. 36 tools. 15 parallel sessions. Stealth. Self-improvement. Up to 10x fewer tokens.
Cinema-grade video production MCP server — 8 tools for recording, editing, effects, captions, TTS, and smart screenshots. Built on ffmpeg + Playwright.
Drive LinkedIn via Playwright, exposed as an MCP server over stdio. Runs standalone (npx) or as an Electron tray app.
Code-aware browser testing agent — 13 MCP tools for AI editors (Claude Code, Cursor, Windsurf). Reads your codebase, opens Playwright, tests everything, reports with screenshots.
CLI and MCP server for kicktipp.com — view leaderboards, schedules, league tables, and place bets from the terminal or through AI assistants like Claude.
Drive Electron apps the way Playwright drives browsers — MCP server for AI agents.
AI-first web scraping engine with stealth bypass, MCP server, and multimodal output (Markdown, JSON, PDF) for agents and automation.
Your app generates its own verified UI transition graph — screens as nodes, guarded (event, effect) edges. Proof-gated verification, trust tiers, model-free MCP for AI agents.
A self-hosted, containerized platform for AI agents, exposed as Capability Packs — schema-validated, one-shot JSON tools — and native MCP. The defining metric is ≥90% pack success on 7B–30B-class open-weight models, something no frontier-targeting competitor is optimizing for.
Free local Google Search MCP server — Playwright-driven, persistent Chrome profile, headless-by-default with CAPTCHA reveal
Secure, session-aware MCP server for ChromiumFish browser automation
Deterministic screenshot diffing for AI coding agents. Extract design tokens, diff implementations vs reference, get CSS fix suggestions.
Headless, agent-controllable real browser as an MCP server — drive local dev servers from Claude. Fast and low-token (DOM, not screenshots). stdio for Claude Code; HTTP connector for claude.ai.
Multi-agent browser MCP runtime for isolated, persistent, parallel Playwright sessions. Run multiple AI agents without shared tabs or browser state.
Unofficial Model Context Protocol server for Alza.cz — read-only catalog browser for AI agents. Uses Playwright to defeat Cloudflare bot protection.
Submit natural language prompts to an AI chatbot, which will use a browser through an MCP (Model Context Protocol) server to perform actions and generate Playwright tests automatically.
MCP server that lets AI agents drive Electron apps — click, type, drag, screenshot, eval JS in the renderer or main process, capture console logs. 38 tools, Playwright-powered, works with any Electron app.
Self-hosted browser automation you own. Record a web task once, replay it forever — as a workflow, a REST API, or an MCP tool. Runs on your box: one SQLite file, no cloud, no telemetry.
MCP server for adding inline, range-anchored comments to Google Docs — the one comment operation the Google Docs & Drive APIs can't do. For AI agents (Claude, Cursor, Copilot) that review documents.
Free Twitter/X MCP server — search, post, read feed, trending — no API key needed. Playwright-based.
Skill + browser MCP for Claude Code and Codex: your app and browser reach domestic services over the real ISP while the agent stays on the VPN. Per-socket binding, per-host routing, no admin, nothing global.
Browser-backed MCP server wrapping mcp-atlassian with Playwright SSO auth for Atlassian Server/Data Center
Multi-agent Playwright MCP server with tab group isolation — multiple AI agents share one Chrome browser
Expose web-only GPT Pro (and any ChatGPT model) to MCP clients via your real, logged-in browser
Unofficial local MCP servers for Genspark image and video generation
MCP server that turns text prompts into premium iOS mobile UI mockups (PNG + HTML). Powered by Claude (Opus 4.7) + Playwright. Two backends: local CLI or Anthropic API. MIT.
🎬 MCP server that records narrated, subtitled tutorial videos by driving a browser with Playwright — captions burned in + .srt sidecar.
An MCP server for Unity that lets AI verify implementations by performing tap, drag, and flick operations on the Game View.
Local MCP server with safe tools for files, Git, browser checks, prompt improvement, skill routing, Notion, Obsidian, RAG, and personal AI workflows.
MCP Tool, that can utilize multiple search engines and processing to provide AI ready results