"Understanding Gemini Thinking or Personality Traits" matching MCP servers:

Enables AI agents to control macOS by capturing screenshots and performing mouse clicks, movement, dragging, text typing, hotkeys, and scrolling, with support for Gemini's normalized coordinate protocol and Retina display scaling.

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.

Windows computer use in the background for Antigravity and Gemini: look at a window, then act in one verified batch with targets named by their label, without taking the user's mouse, keyboard or foreground; irreversible actions need explicit confirmation.

This server enables AI agents to operate Windows and Linux computers by observing the screen, understanding the UI through accessibility, OCR, and vision, and performing mouse, keyboard, window, clipboard, and system actions with verification and recovery.

Enables AI agents to capture and inspect a window, send background clicks, keys, text and scrolls, and write, validate, run and monitor YAML automation scripts (or watchers) so fast reactive work is handled without the agent's thinking latency.

A high-performance Model Context Protocol (MCP) server built for Windows. Leveraging the native Everything SDK, it provides AI models (like Claude, GPT, Gemini) with millisecond-speed file searching, statistical analysis, and disk usage insights.

Remote-first, model-independent Windows execution MCP for ChatGPT, Claude, Gemini, and other MCP-compatible AI clients.

Enables AI clients on Windows to control the local mouse, keyboard, and screen understanding via MCP stdio, allowing automated workflows like viewing the screen, locating elements, clicking, typing, and verifying results.

A server that provides rich UI context and interaction capabilities to AI models, enabling deep understanding of user interfaces through visual analysis and precise interaction via Model Context Protocol.

Enables MCP agents to drive Windows applications by targeting individual windows—clicking, typing, scrolling, dragging, and reading accessibility trees or screenshots—without stealing the user's focus, mouse, or keyboard. Runs entirely locally alongside the user, with per-app approval and no cloud account or usage limits.

Lets MCP clients discover and run AppleScript or JavaScript for Automation (JXA) to control macOS applications, inspect the system, or reuse scripts from a bundled knowledge base.

Allow AI agents to see and control a real Windows PC you own: observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH — your machine, your key.

Clones the OpenCode workbench installation onto Linux machines — locally or over SSH — reproducing the same OpenCode config, MCP servers, agent skills, plugins, and Docker tooling. Exposes 6 tools over stdio.

Enables AI agents to capture and analyze screenshots of macOS applications, windows, or the entire screen using local (Ollama) or cloud-based AI vision models, with non-intrusive, fast screen capture via Apple's ScreenCaptureKit.

Run Apple Shortcuts on your iPhone, iPad or Mac from any MCP client over an end-to-end encrypted relay. The phone can stay locked.

Enables MCP-compatible AI clients to securely monitor and manage a self-hosted Linux VPS over SSH, including service status, disk and RAM usage, TLS certificate expiry, fail2ban summaries, and two-step confirmed service restarts or IP unbans.

Enables an MCP client such as Claude to inspect a Mac's battery, memory, CPU, GPU, disk, and most energy-hungry apps, and to shut down, restart, sleep, or lock the screen now or on a schedule with a cancellable 60-second grace period.

Enables an AI assistant to list available monitors and take a single on-demand still screenshot of a selected monitor, with optional downscaling and JPEG or PNG output.

Enables AI tools to open the macOS Maps app and search for places or addresses through a single MCP tool, without requiring a Maps API key.

Provides AI agents with real-time ground truth about what's actually running on the machine, including live agent sessions, listening TCP ports, loaded daemons, and system stats. It reads directly from the OS via fixed commands, ensuring agents never rely on stale docs or transcripts.

Inspect a cronstable job scheduler's jobs, logs, run history, DAG workflows, and cluster health, and ask why a job did or didn't run. Read-only by default; tools that run, pause, or approve jobs and workflow runs need opt-in.

Control a real iPhone or iOS Simulator through a macOS daemon and XCTest runner over USB or Wi-Fi: read screen text, tap, type, swipe, inspect logs and replay flows with explicit outcomes. Browser sandbox: use readonly to inspect 12 preloaded flows without a phone. Reuse an existing sandbox from MCP Deployments, or delete it before starting another. Device control needs your Mac and iPhone.

Enables Large Language Models to automate macOS applications and execute AppleScript commands through natural language. It features built-in security protections including application allowlists and dangerous pattern detection to prevent unauthorized or risky system operations.

jobd is a self-hostable, GPU-aware job broker that queues and routes shell commands across your own machines — picking workers by available VRAM and tool tags, streaming logs back, and surviving across sessions. It ships native MCP integration, so agents can submit, monitor, and control long-running or GPU jobs as tools.

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

Enables MCP clients to access a local computer through a controlled, permission-based tool surface for read-only or developer-mode file, process, and terminal operations.

Lets AI agents use an Android phone: read the screen, tap, type, scroll, open apps, take screenshots and reply to notifications, with approval cards before anything is sent, posted, bought or deleted. Runs inside the Buddy app on the phone; no root, adb or PC.

Enables agents to perceive and control a Windows desktop, a connected local Chromium browser, or a cloud Playwright browser through human-like mouse moves, clicks, drags, scrolling, and screenshots, forming an observe-locate-act computer-use loop. Includes safety guards such as random pauses, emergency stop, and approval prompts for destructive actions.

Enables AI agents to see and drive a real Android phone over plain ADB: screenshots and numbered UI trees, gestures, typing with accents and emoji, SMS/RCS reading and prepared replies, notifications, files, and settings, with no root and no app installed on the phone. Safeguards mask security codes and require explicit confirmation before sending, paying, deleting or confirming anything.

Enables background window capture and input automation without moving the cursor or stealing focus, working across Windows, Linux X11, and Wayland systems.