open-computer-use
Lets AI agents see and control desktop applications through the accessibility layer, enabling clicking, typing, scrolling, dragging, and window/app management across macOS, Windows, and Linux entirely on the local machine.
README
<p align="center"> <img src="./assets/logo/open-computer-use-256.png" width="144" alt="open-computer-use"> </p>
open-computer-use
A local MCP server that gives AI agents eyes and hands on your desktop. Agents can see an app's interface, click, type, scroll, and drag — through the accessibility layer, without taking over your real mouse and keyboard. Runs entirely on your machine, on macOS, Windows, and Linux.
The tools
Nine core tools, identical across all three platforms:
| Tool | What it does |
|---|---|
list_apps |
List running and recently used applications. |
get_app_state |
Read an app's accessibility tree and screenshot. |
click |
Click by element_index or screenshot coordinates. |
perform_secondary_action |
Invoke an element's own secondary action. |
scroll |
Scroll an element by pages, or a window by pixel deltas. |
drag |
Drag between two coordinates. |
type_text |
Type text, Unicode-safe, background-first. |
press_key |
Press a key or chord (ctrl+s, return, page_up…). |
set_value |
Set the value of a settable control directly. |
Five additional window-level tools — list_windows, get_window, get_window_state, launch_app, activate_window — follow the newer window2 API and are currently available on Windows (macOS and Linux in progress).
Quick start
npm i -g @opensymph/open-computer-use
ocu doctor # verify the install; macOS: prompts for permissions
ocu call list_apps
macOS 14+ needs Accessibility and Screen Recording granted once. Windows and Linux work out of the box in a signed-in desktop session (Linux desktops need AT-SPI2, which GNOME and friends ship by default).
No npm? Grab the tarball from GitHub Releases and run npm i -g <tarball> — or install it into ZCode as a plugin (below) and it will use whatever local runtime it finds.
Connect your agent
ocu install-codex-mcp # Codex CLI & Codex App
ocu install-codex-plugin # Codex App, plugin form
ocu install-claude-mcp # Claude Code
ocu install-gemini-mcp # Gemini CLI (--scope user for global)
ocu install-opencode-mcp # opencode
Any other MCP client — add it manually:
{
"mcpServers": {
"open-computer-use": { "command": "open-computer-use", "args": ["mcp"] }
}
}
ZCode
This repo ships as a ZCode plugin — one install gives you the skill and an auto-connected MCP server:
-
Install the runtime once (the plugin falls back to it when no local build exists):
npm i -g @opensymph/open-computer-use -
In ZCode, open Settings → Plugin Management → Discover and click +.
-
Add this repository — the GitHub URL
opensymph/open-computer-use, or a local checkout directory. -
Find Open Computer Use in the list and click Get.
-
Start a new session. Check Settings → MCP shows
open-computer-useas connected, then just ask: "list the windows on my screen".
To remove it later: Installed tab → Open Computer Use → uninstall.
Agent skill — installable guidance that teaches agents to use these tools well:
npx skills add opensymph/open-computer-use -g -a claude-code --skill open-computer-use -y
Why this one
- Non-intrusive by design. Prefer the accessibility API over synthetic input; your real pointer, focus, and foreground app stay put unless you explicitly opt into global input.
- Three platforms, one contract. The same tool names, arguments, and results on every OS — agents don't need per-platform branching.
- A cursor you can watch. On macOS, actions drive a visible software cursor, so you can follow what the agent is doing.
- Scriptable without a client.
ocu callruns any tool from your shell and prints MCP-style JSON;--callschains sequences in one process. - Guardrails built in. Password managers are always refused. Launching apps, stealing focus, and global input injection each sit behind an explicit environment-variable gate.
- Signed where it matters. The macOS runtime is Developer ID signed, so granted permissions survive version upgrades.
Platform status
| Platform | Runtime | Notes |
|---|---|---|
| macOS | Swift | Visual cursor, permission onboarding, sky_click background clicks. |
| Windows | Go, single exe | UI Automation + Win32, process-isolated operations, full window2 API. |
| Linux | Go, single binary | Native AT-SPI2 over D-Bus, zero runtime dependencies. |
Documentation
- Architecture — how the three runtimes work
- Skill references — usage, installation, troubleshooting
- Security policy and third-party notices
- Contributing
License
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。