"Claude AI Extension or App for Safari Browser" matching MCP servers:

Enables an AI agent to operate a spare Android phone through MCP: capture screenshots, inspect UI controls, tap/swipe, input Chinese text, launch apps, and optionally run rooted shell commands or transfer files. It also supports a live web console for remote viewing and control.

An MCP server for comprehensive browser automation and full local PC control via shell commands and Python execution. It enables tasks like web navigation, file system management, and remote access through SSE with token authentication.

MCP server that lists, installs, and removes applications on Linux targets via Peckboard, supporting local and remote SSH hosts with distro package managers and pip.

Central daemon for managing local app processes, enabling multiple Claude Code sessions to coordinate starts, stops, and restarts with conflict resolution and a web dashboard.

This MCP server enables natural, humanized control of a real Chrome browser from Cursor agents, simulating natural mouse paths, typing cadence, and scroll pauses for click, type, scroll, and navigate actions via a Chrome extension.

A fast MCP server for opening, focusing, and quitting macOS apps, and opening URLs in the browser, usable by voice or from any MCP client.

Give Claude Desktop full desktop control on Linux/X11: screenshot, mouse, keyboard, windows, clipboard, app launch. Zero-dependency MCP extension, MIT-licensed.

Give Claude Desktop terminal, filesystem, and background-job access on your local Linux machine. Zero-dependency MCP extension, MIT-licensed.

Enables Claude Code to read and operate macOS app interfaces through the accessibility tree, pressing buttons, setting text fields, typing with IME support, sending shortcuts, scrolling, dragging, and capturing screenshots. It drives background apps without moving the mouse or stealing focus from the user's current work.

An MCP server that enables remote observation and control of a Chromium browser via a WebSocket relay, supporting DOM, CDP, and native OS automation for local or LAN-based AI agents.

A Windows-only MCP server for controlling a real browser using native screenshots, Windows accessibility, and node-interception mouse/keyboard input, without CDP or Playwright.

Enables AI agents to directly control your real Chrome browser with full context including login sessions, cookies, and open tabs. It provides tools for page scanning, JavaScript execution, CDP control, screenshots, and physical mouse/keyboard input for authentic browser automation.

Enables mobile device automation for Android (via ADB) and iOS Simulator (via simctl), allowing you to control devices with natural language through screenshots, UI interactions, text input, and app management.

MCP server that controls remote desktop environments over VNC, using a JS proxy layer and a native Swift VNC daemon.

MCP server that allows AI coding assistants to schedule deferred tasks such as reminders, shell commands, and AI prompts, executing them as an OS daemon.

Full computer control for AI agents on macOS — see, click, type, scroll via MCP. Works with any app, all processing on-device with PII protection.

Enables AI assistants to find and launch Windows applications by name using multi-strategy discovery via registry, Start Menu, PATH, and common directories.

Launch Windows applications by name, alias, or path via MCP, supporting arguments and working directories. Uses Task Scheduler to detach launched processes so they persist independently of the MCP server.

Lets Claude create, list, edit, run, and delete one-click script buttons that appear on a bar docked to the Claude desktop window. Scripts run locally without prompts or token usage, automating routine tasks like pulling git repos or backing up folders.

Enables MCP clients to control a Linux/X11 desktop like a human: see the screen, move the mouse, click UI elements via the accessibility tree, type text, and manage windows.