"How to control a computer" matching MCP servers:

Enables computer control via mouse, keyboard, OCR, and screen/window management, similar to Anthropic's computer-use.

MCP server that provides computer control capabilities including mouse movements, keyboard actions, screenshot capture with OCR, and window management through a unified API.

Provides native macOS computer control tools including mouse and keyboard simulation, screenshot capture, and application management for MCP-compatible agents. It enables AI assistants to directly interact with the macOS operating system and installed apps through standard tool calls.

Enables low-cost agent models to control Windows applications through a compact, state-safe proxy over Open Computer Use, reducing model-visible context by up to 99.8% with support for record/replay and reusable UI component memory.

MCP server for Windows computer use, providing low-token, low-latency automation through UIA/Win32, OCR, and vision. It enables batch actions, shortcuts, isolated desktop execution, and browser control via MCP tools.

Enables AI assistants to control Ubuntu desktops through screenshots, mouse clicks, and keyboard interactions using AT-SPI integration and computer vision. It features optimized element detection and workflow batching for fast and accurate visual interaction with desktop applications.

Native Windows MCP server that gives AI agents full desktop control. 45+ tools using UIAutomation + OCR with automatic dark theme enhancement instead of screenshots. Features batch action sequencing (run_sequence), window occlusion detection, menu navigation, PrintWindow capture, and embedded AI workflow instructions. Single .NET 8 executable — no Python, no Node, no Selenium.

Windows原生桌面自动化MCP服务器，提供22个工具用于窗口管理、输入控制、截图、OCR和智能元素匹配。

Enables AI agents to operate websites and Windows desktop applications by reading and acting on webpage elements, exposed UI controls, and screenshots with mouse and keyboard input. Combines browser, desktop, and computer-control channels in a single task, with an optional target selector for batched actions.

Enables any compatible MCP harness to control macOS apps through OpenAI's Computer Use backend, with explicit approval checks.

Enables AI agents to observe and operate a real Windows or Linux desktop like a human — snapshotting screen geometry, active window, OCR text and normalized UI elements, then clicking, typing, scrolling and managing windows with built-in verification and recovery. Backends are chosen automatically per action (UIA/AT-SPI → OCR → vision → PyAutoGUI), so browsers, IDEs, office suites and canvas apps are all controllable without any browser-automation MCP.

Listens for Discord @mentions via Gateway and queues them for processing by an agent, exposing a tool to retrieve pending mentions for automated responses.

Enables AI-driven job application automation for LinkedIn and SEEK platforms with intelligent cover letter generation, automated application submission, and application tracking management. Supports anti-detection measures and complies with platform usage policies for safe job hunting automation.

Enables agents to convert Markdown into WhatsApp-compatible formatting, including styled text, lists, and tables that fit a phone's monospace width.

Enables AI apps to work with Google Sheets in plain language: finding spreadsheets, reading and writing ranges, managing sheets, formatting, validation, protected ranges, tables, charts, and access control, with deliberate writes and destructive operations clearly marked.

Enables AI assistants to manage Google Contacts through natural language, including searching, reading, creating, updating, and deleting contacts, organizing labels and groups, running batch operations, and converting auto-saved Other contacts into regular ones.

Enables AI assistants to search, read, draft, and send Gmail messages, as well as manage labels and trash using natural language.

Enables coding agents to perform computer use across browsers and native Windows apps by observing the screen, reducing it to a finite list of executable candidates, and letting a small decision model choose one action before input is sent and the result verified. It also returns per-goal outcomes, uncertainty handoffs, and run journals so the calling agent can recover from failures.

MCP server that gives Claude and other MCP hosts full access to Calendar.app on macOS — list, search, create, update, and delete events across all configured accounts.

Minimal MCP server for sending messages to Poke via the inbound webhook.