RaroCUA
Local installio.github.mectrojohnny/raro-cua
Local macOS Computer Use MCP server with screenshots, AX trees, and app actions.
336 servers in Browser Automation
Local macOS Computer Use MCP server with screenshots, AX trees, and app actions.
MCP server for Chrome DevTools
Control this Windows desktop from any MCP client: files, windows, keyboard and mouse.
220 browser automation tools for Chrome, Edge, and Firefox via CDP + BiDi. 100% Python.
Browser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.
Give any LLM agent a real Android or iPhone as its body. 62 MCP tools for mobile automation.
Control the MetaDock desktop workspace over MCP: browsers, layouts, bookmarks, downloads, and more.
Ultra-lightweight browser engine for AI agents. 33 MCP tools, 4 SDKs, cross-platform.
GNOME Wayland desktop automation via AT-SPI discovery and Mutter input.
Debug PWAs in your real browser via MCP: service-worker, cache, installability & framework state.
Control Firefox browsers (Floorp, LibreWolf, Zen, Firefox) from any MCP client.
MCP server for desktop, browser (CDP), and Android automation. Screenshot, OCR, click, type.
MCP server for parallel browser automation across multiple providers.
Browser automation MCP server with 84 tools. Pure CDP, DOM diffing, vision hybrid.
MCP server for macOS desktop automation via the Accessibility API.
Cloaked headless browser for AI agents — stealth TLS, smart extraction, SPA fallback
Windows screen capture MCP server with display, region, and active-window capture tools.
MCP server for Safari DevTools — browser debugging and automation for AI coding agents
Browser tasks, sessions, and recipes for MCP and HTTP automation.
Token-efficient browser agent for local LLMs. Playwright + accessibility tree + MarkGrab.
AI personas navigate your web app in real browsers, find bugs and UX issues. No scripts needed.
Capture webpage screenshots with format, viewport, and dark mode options
Visual Desktop Bridge - Give any AI full control over Windows to automate apps and inputs.
Hands your live Chrome tab to any MCP client — snapshot, navigate, click, type, extract.
Browser tasks, sessions, and recipes for MCP and HTTP automation.
Drive your real, logged-in Chrome/Edge from AI agents over CDP. Faster. Sharper.
Windows desktop-control MCP server: screenshot, window mgmt, mouse/keyboard input, recording.
Capture & annotate your screen from an AI agent: arrows, boxes, text, highlight, blur/redact.
A zero-LLM MCP server that replays recorded site maps instead of re-exploring browser routes.