- Conduid
- Marketplace
- #gui-automation
MCP servers tagged gui-automation
34 live MCP servers tagged "gui-automation", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with gui-automation.
Computeruseprotocol
Computer Use Protocol is a universal schema for AI agents to perceive and interact with any desktop UI.
Tkinter MCP Server
A Model Context Protocol (MCP) server that enables AI agents (like Claude) to view, introspect, and control Tkinter GUIs. Features widget-tree extraction and window-specific scree…
CaoGen
CaoGen — a vendor-neutral, local-first AI work desktop. Multi-provider agent runtime, GUI automation, MCP, Git worktree, task orchestration, effect ledger, and 3D office workspace…
EastGenesis
CaoGen — a vendor-neutral, local-first AI work desktop. Multi-provider agent runtime, GUI automation, MCP, Git worktree, task orchestration, effect ledger, and 3D office workspace…
AutoControlGUI
A framework for GUI automation
Munim Computer Use
Empower AI agents to control browsers and desktops, automating complex tasks with natural language commands.
Pi Vision Struct
⛔ 已停止维护（EOL 2026-09-13，仓库只读）· Deprecated & archived：给纯文本模型的数理化视觉通道 + GUI 控制；已被 DeepSeek-V4.1 原生多模态取代。Numeric-grade vision channel + GUI control for text-only models — superseded b…
Macos Computer Use Kit
AX-first computer use for AI agents on macOS with optional Jev (TypeSafe System One) semantic guards: calibrated target/input judgments before an irreversible action, decisions ke…
Panoptes
面向 AI Agent 的屏幕操作 MCP 服务器 — 截图 + 鼠标键盘控制，9 个工具经 Streamable HTTP 上的 JSON-RPC 2.0 暴露
Vroid
Drive VRoid Studio from any MCP client — Wayland GUI automation with OCR + virtual pointer
Uictl Win MCP
Windows (.NET/C#) GUI-automation CLI/MCP server for coding agents
Plugshell
An agent-operable host for audio plugins: read parameters and presets, see the editor, and operate the controls that are not exposed as parameters.
Windows Gui MCP
Windows GUI Automation MCP server for AI coding agents
Sloth MCP
MCP server that lets Claude use your Mac — native apps and the browser — by remembering what it has seen instead of screenshotting every step.
Eyehands
Local HTTP server that gives AI agents eyes and hands on Windows
Universal Computer Control
MCP server that gives AI agents universal control of any computer — observe, click, type, verify. UIA/AT-SPI → OCR → vision → PyAutoGUI fallback. Win/Linux.
Reflex Cu
Computer use MCP server for Claude Code, Codex and other AI agents. Reads the UI tree instead of taking a screenshot every step, with Jev (TypeSafe System One) as a fast judge. Lo…
Background Computer Use
MCP server + skill library for driving macOS apps in the background — click, type, scroll, and inspect accessibility trees without activating apps or moving your cursor. Works wit…
Helix Pilot
GUI automation MCP server powered by local Vision LLM (Ollama). Control your Windows desktop from Claude Code, Codex CLI, and other MCP clients.
SoftAuto MCP
Open-source Windows RPA and MCP server for AI agents — UIA desktop automation, browser DOM automation, ERP workflows, and fast element-level execution beyond screenshot-by-screens…
PyMCPAutoGUI
🚀 赋予 AI Agent (如 Cursor, Claude) 视觉与操作能力的跨平台 MCP 服务端。让大模型像人类一样看屏幕、控键鼠、管窗口！(A GUI manipulation MCP server for AI Agents)
Gui Agent
Lightweight, ultra-fast FastMCP server for Computer Use & GUI automation on Linux and Windows (Mouse, Keyboard, OCR, Video, Web).
Computer Control
Cross-platform desktop and mobile-simulator automation in C++20 — macOS, Windows, Linux, iOS simulators and Android emulators. Native library, stable C ABI, CLI and MCP server.
Haiku Control MCP
MCP server for controlling Haiku
Symaira Cockpit
One command for your Mac: tune thermals, power and display, inventory local ports, containers and MCP servers, automate the interface. A native macOS CLI with JSON output — and an…
Uictl Mac MCP
macOS GUI-automation CLI/MCP server for coding agents
WinControl MCP Driver
WCMD 讓你的agent可以控制你的電腦without only using command
Spooky Action
Computer use on a Mac for any AI agent. It presses the button, not a pixel — through the accessibility layer, so your cursor never moves. Watch it work, and take the screen back b…
ControlFreak
A native Windows MCP server for safe, visible computer use and desktop automation.
Mynd Platform
MYND — AI Agent Platform: GUI automation, persistent memory, multi-agent orchestration, skills marketplace, MCP integration. Core of the MYND ecosystem.
Claude Workman
Computer use for Linux as an MCP server — an AI assistant sees the screen, reads the accessibility tree, then clicks and types. Works with Claude, Claude Code, and any MCP client.
Clickproof
Content-addressed GUI action facts for computer-use agents
MacWork
Open-source computer-use agent and MCP server for macOS — operates any app through the Accessibility API and native interfaces instead of screenshots. No app-specific code.
Winagent Lite
Local vision-driven Windows GUI agent with a reproducible benchmark