Browser Automation MCP Servers for Codex CLI

See and drive any Windows app via the accessibility tree - no screenshots - plus 200+ native tools

Background Windows desktop for AI agents: native GUI automation, screenshots and app testing.

Pre-computed navigation recipes for public websites — skip explore-and-discover.

MCP Server for BNBOT Chrome Extension - Control Twitter/X via AI assistants like OpenClaw

Screenshot every website in a dataset, CSV or Google Sheet, desktop and mobile, as image links

Persistent Linux computers for AI agents: desktop, signed-in browser, vault, apps and shell.

Capturewren: screenshot any URL (banners removed) plus status, title and clean page text for agents.

Drive the iOS Simulator from a coding agent, with every action verified.

See any site as it looks on a real iPhone, iPad or MacBook — and drive that window over MCP.

Computer use for your agents across the Omarchy machines you own. Open source MCP server.

Mac app that lets AI agents drive iPhones, iOS simulators and Android: tap, type, install, logs.

Android device automation for AI agents: MCP server, CLI, and plugin runtime over adb.

A 659 KB Rust binary driving the OS WebView — no Chromium. 16 MCP tools for AI agents.

Secure AI access to Windows, macOS, Linux computers and a hosted Cloud Browser.

A real Safari-engine (WebKit) browser for agents on macOS: sessions, extraction, bot checks.

Drive macOS apps without taking the cursor: read, click, type, scroll, each with evidence.

Screenshot any public web page from an AI agent. Free without signup, or with an API key.

Live browser debugging for AI assistants — DOM, console, network via MCP.

Measures your site in a real browser and returns verifiable observations, with evidence and limits.

Visible Electron browser driven by a semantic accessibility tree: 17 MCP tools, no screenshots.

Capture website screenshots, run bulk captures, and manage screenshot schedules and history.