"Creating the Best General-Purpose Agent" matching MCP servers:

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Provides AI agents with environmental sensing capabilities including current time, IP-based geolocation, system information, and hardware details. Enables more contextual and accurate AI responses based on user's environment.

Web agent that keeps working when a task leaves the browser: deterministic routing between the page DOM and Windows UI Automation, with LLM-free skill replay.

A local MCP server for trusted NixOS automation that enables inspecting files, applying patch sets, and validating/switching NixOS or Home Manager configurations.

MCP server that lets a private ChatGPT app remotely control a paired Windows PC, including files, PowerShell, programs, screenshots, mouse/keyboard, clipboard, and Chrome.

Enables a private ChatGPT app to remotely control a Windows PC through file operations, PowerShell, screenshots, mouse and keyboard input, clipboard, and Chrome browser automation.

A local MCP server that controls Android devices via ADB, enabling AI agents and users to manage devices, execute UI automation, and perform testing through 27 MCP tools and an optional web console.

A read-only MCP server that lets local AI agents inspect open Mac windows, browser tabs, PDFs, clipboard contents, Finder selections, and Messages history so they can answer questions about what the user is currently viewing.

Enables AI agents to control a Linux desktop and browser through governed tools for mouse, keyboard, windows, clipboard, screenshots, navigation, and page interaction, with policy verdicts, human confirmation, secret redaction, and an append-only audit trail.

Enables AI agents to automate a Linux desktop natively on Wayland, with 68 tools for screen capture, input simulation, browser automation, OCR, accessibility, media, audio, clipboard, notifications, filesystem, system, memory, and network operations through the MCP protocol.

Gives a coding agent its own Docker-hosted Linux desktop with XFCE, Chromium, Blender, LibreOffice, GIMP and a sudo shell, exposing tools for screenshots, mouse and keyboard input, window focus, shell commands, file read/write, opening URLs or GUI apps, and headless Blender renders. The agent can watch and drive that desktop live from a browser while working on the shared project folder.

Enables an AI agent to operate a real computer through ScreenMirror—looking at the screen, acting, and checking its work—while requiring a person's consent for each separately granted capability.

Enables AI assistants to capture screenshots and control desktop input (mouse, keyboard) to see and interact with your screen. Features user-first safety controls including automatic pause on user activity and app allowlists to restrict interactions to approved applications only.

Enables AI agents to control a physical Android device or Docker-hosted emulator over ADB by taking screenshots and performing taps, swipes, key presses, text input, shell commands, app launches, and device info queries. It runs as a local MCP stdio server alongside a web UI and REST API for remote access.

A local MCP server that lets AI agents see and operate real iPhones, iPads, and Android devices from a Mac — screenshots, on-device OCR, taps, swipes, typing, app launching, and replayable skills over USB, Wi-Fi, or adb, with nothing installed on the phone. It gates anything that sends, posts, buys, or deletes behind human approval dialogs and private credential entry, backed by a kill switch, policy file, audit log, and a live-view web console.

Enables macOS computer use through the agent-desktop CLI: accessibility-tree snapshots with refs, headless clicks, typing, key presses, scrolling, screenshots, clipboard access, waits, and batch actions across 21 tools. Acts as a drop-in replacement for the bundled kimi-cu plugin, without moving the cursor or stealing focus for most operations.

A Windows desktop automation MCP server that enables UI recognition through OCR, UIA controls, and multi-point color matching. It allows agents to interact with desktop applications via actions like clicking and typing while using a learning system to track and improve operation success.

Agent Droid Bridge gives AI agents programmatic control over Android devices and emulators via ADB, exposed as an MCP server.

An MCP-only server that launches AI CLI tasks (Claude, Codex, Gemini, Forge, OpenCode) as background subprocesses and manages them via PID for status, output, and lifecycle control.

Enables AI agents to call native macOS calendars, reminders, files, desktop/system actions, selected Apple apps, shortcuts, and web tools through MCP, with scoped file access and explicit approvals for writes.

Enables provider-neutral automation of dedicated Linux desktop applications across private X11, KWin/Wayland, headless Chromium, and explicitly enrolled Sway sessions through MCP. It supports input, screenshots, window targeting, cancellation, timeouts, and crash recovery while reporting each backend's limits.

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.

Local MCP server for observing and controlling an authorized Android device over USB using ADB and scrcpy, providing screen capture, UI automation, app inspection, logcat, and evidence recording.

Enables AeyeStudio AI chat to securely access and control local PC resources such as files, Excel, clipboard, apps, and shell through a localhost MCP agent with user approval.

Enables AI-driven phone management for Android and iOS devices, including flashing, unlocking, and automation via MCP.

Local MCP server for Gateway-managed computer use that exposes computer.* tools with desktop control, OCR, and user-visible safety overlays.

An MCP server and CLI for controlling FarmBot hardware, enabling AI agents to manage gardening tasks through tools like gantry movement and device status monitoring. It supports executing Lua scripts and core hardware commands like homing and emergency stops via the Model Context Protocol.

Enables Codex to observe a physically separate computer or tablet through HDMI capture and control it with USB HID keyboard and mouse, pairing each action with the latest observation.

Exposes native iPhone device services and UI automation through MCP, enabling agents to inspect and control trusted iPhones via a unified interface.

A Skill for your agenic AIs Like Claude Code, Codex or Antigravitty that lets you organise your messy files!