Browser Automation MCP servers

Open Korean e-Gov and finance sites in a clean, disposable Windows Sandbox with security programs.

Local-only Chrome and Edge control for MCP clients through an origin-scoped extension.

Plain-English browser tests for AI agents: real Chrome, deterministic verdicts. Free, no API keys.

See and drive a whole Windows machine from Bun — apps, input, screen, OCR, registry, OS — via MCP.

KATATAN E2E testing agent set — Playwright + KATATAN MCP integration

Complete 49 CFR 172.101 hazmat table lookup with special-provision decoding, cited to eCFR.

Stealthy, LLM-drivable browser engine — a Python library + 85-tool MCP server on stealth Chromium.

Browser automation using Playwright with optional stealth mode to bypass anti-bot protection.

Capture website screenshots from any MCP client via the ScreenshotRender API.

Drive a stealth-patched Chromium daemon: navigate, screenshot, eval JS, attach over CDP.

An MCP Server for computer-use in Windows OS

MCP server that gives AI agents dynamic network chaos control over Playwright browser sessions

Create and control browser sessions for web automation, testing, and AI agent tasks

Goal-driven Playwright browser sessions for LLMs, with full action traces and aria-snapshots.

Control Android/iOS/Windows devices from Claude, Cursor, and other AI tools. iOS without jailbreak.

Local Chrome via CDP with profile-snapshot isolation and shared-broker multi-client support

Hosted Playwright API for AI agents. Returns a11y trees instead of screenshots.

Take Wayland screenshots via grim/slurp. Full screen, region, or interactive crop.

Multi-session browser MCP — 15 parallel isolated browsers, 37 tools, stealth, self-improvement.

Let AI agents interact with any website through natural language instead of CSS selectors

Spatial DOM maps for AI agent browser navigation with anti-bot stealth.

Stealth browser MCP server — anti-detection Chromium with snapshot-first agent interface

Control Windows desktop via MCP: mouse, keyboard, screenshots, clipboard, and apps.

AI-native browser for agents. 71 tools with self-healing, semantic extraction, vault CLI.

Screenshot API for MCP clients. Capture any URL as PNG with mockup mode support.

57 tools for AI-powered iOS Simulator automation — tap, swipe, type, screenshots, and more.

Browser engine for AI agents. HTML in, Semantic Object Model out. 16x fewer tokens.

AI control of Android/iOS devices. Screenshots, UI tree, AI vision, Flutter, video. 49 tools.