PluginBench
Skill
Review
Audit score 70

open-computer-use

ifuryst/open-codex-computer-use

Platform-neutral CLI and MCP server for GUI automation across macOS, Linux, and Windows.

What is open-computer-use?

Open Computer Use is an open-source Computer Use MCP server and CLI that exposes desktop automation tools like clicking, typing, scrolling, and app state inspection. Use it when an agent needs to interact with graphical applications or verify system state across macOS 14.0+, Linux, or Windows.

  • List and inspect running applications and their UI state
  • Click, type, scroll, and drag within application windows
  • Capture full or partial UI trees with configurable text and node limits
  • Perform secondary actions and set control values programmatically
  • Run as a local stdio MCP server or standalone CLI with direct tool calls
  • Support multi-step sequences in a single process to reuse element indexes

How to install open-computer-use

npx skills add https://github.com/ifuryst/open-codex-computer-use --skill open-computer-use
Prerequisites
  • macOS 14.0 or later (for macOS); Linux or Windows with a logged-in desktop session
  • Installation via npm: `npx skills add https://github.com/ifuryst/open-codex-computer-use --skill open-computer-use`
  • On macOS, Accessibility and Screen Recording permissions must be approved in system settings
Claude Code
Cursor
Windsurf
Cline

How to use open-computer-use

  1. 1.Verify the CLI is installed by running `open-computer-use -h` or `ocu -h`
  2. 2.On macOS, run `open-computer-use doctor` and approve any permission prompts before the first GUI task
  3. 3.List available apps with `open-computer-use call list_apps`
  4. 4.Capture the current UI state of a target app using `open-computer-use call get_app_state --args '{"app":"AppName"}'`
  5. 5.Perform actions by referencing element indexes from the latest state: `open-computer-use call click --args '{"app":"AppName","element_index":"0"}'`
  6. 6.For sequences, use `open-computer-use call --calls '[...]'` to reuse element indexes across multiple tool calls in one process
  7. 7.For MCP integration, configure `open-computer-use mcp` in your agent's MCP server config and call Computer Use tools directly

Use cases

Good for
  • Automating repetitive GUI tasks like form filling or data entry across desktop applications
  • Capturing and analyzing application state for testing or verification workflows
  • Orchestrating complex multi-app workflows where agents need to coordinate clicks and text input
  • Debugging desktop application behavior by inspecting UI trees and app state
  • Running GUI automation in CI/CD or headless environments on Linux or Windows
Who it's for
  • AI agents and coding assistants that need to control desktop GUIs
  • Developers building automation workflows across multiple platforms
  • QA and testing teams automating GUI-based test scenarios
  • System administrators automating cross-platform desktop tasks

open-computer-use FAQ

What macOS versions are supported?

macOS 14.0 or later. Older versions cannot run the binary; permission changes or `doctor` will not fix binary incompatibility.

Can I use this on Linux and Windows?

Yes. Linux and Windows use their own platform runtimes and do not have a macOS version requirement. Both require a logged-in desktop session.

What if permissions are missing on macOS?

Run `open-computer-use doctor` and approve Accessibility and Screen Recording in the system settings onboarding UI.

How do I use this with my AI agent?

Either run CLI commands directly (e.g., `open-computer-use call list_apps`), configure it as an MCP server in your agent's config, or use `ocu js` / `ocu repl` for direct code orchestration.

Should I use element_index or coordinate-based clicks?

Always prefer element_index from the latest `get_app_state` result. Use coordinate clicks only when the element tree does not expose a safer target.

Full instructions (SKILL.md)

Source of truth, from ifuryst/open-codex-computer-use.


name: open-computer-use description: Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.

Open Computer Use

Overview

Open Computer Use exposes Computer Use as a local CLI and stdio MCP server. It is not Codex.app-specific; adapt the commands and MCP config to the agent runtime you are operating in.

The macOS runtime requires macOS 14.0 or later. Windows and Linux use their own platform runtimes and are not subject to this macOS minimum.

It supports the same core tool surface across macOS, Linux, and Windows: list_apps, get_app_state, click, perform_secondary_action, scroll, drag, type_text, press_key, and set_value.

Core Workflow

  1. On macOS, run sw_vers -productVersion before invoking the CLI and require macOS 14.0 or later. On older versions, explain that the runtime cannot launch; do not recommend doctor or permission changes as a fix for binary incompatibility.
  2. Check the CLI is installed with open-computer-use -h or ocu -h. If installation or setup is missing, read references/installation.md.
  3. On supported macOS versions, run open-computer-use doctor before the first real GUI task. If permissions are missing, ask the user to approve Accessibility and Screen Recording in the onboarding UI.
  4. Inspect available apps before acting: open-computer-use call list_apps.
  5. Capture current UI state with open-computer-use call get_app_state --args '{"app":"TextEdit"}'. The default state is usually enough for UI operation.
  6. When the task needs longer semantic text, such as chat history, email bodies, document text, or long form content, call get_app_state with text_limit: 1000 or text_limit: "max".
  7. When visible long pages or lists appear incomplete even after scrolling, call get_app_state with a larger max_tree_nodes or max_tree_depth.
  8. Prefer element-targeted actions using element_index from the latest get_app_state result.
  9. For multi-step CLI work, use open-computer-use call --calls '<json-array>' so one process can reuse the latest element index mapping.
  10. For agent runtimes that support local MCP servers, configure open-computer-use mcp or ocu mcp and call the exposed Computer Use tools directly. Read references/usage.md.
  11. For direct code-first orchestration, run ocu capabilities and then use one-shot ocu js or persistent ocu repl. Read references/usage.md.
  12. If communication, permission, or desktop-session access fails, read references/troubleshooting.md.

Operating Rules

  • Treat the target desktop as the user's real session. Do not inspect password managers, unrelated private content, or sensitive apps unless the user explicitly asked for that task.
  • Ask before sending, deleting, purchasing, approving, uploading, or making other externally visible changes.
  • Do not assume Codex.app plugin helpers are available. Use the installed open-computer-use / ocu CLI or an explicit MCP config.
  • Always run get_app_state before using element_index; do not guess indexes across sessions or after large UI changes.
  • Prefer semantic actions and set_value for editable controls. Use coordinate click, scroll, and drag only when the element tree does not expose a safer target.
  • On macOS, do not enable OPEN_COMPUTER_USE_ALLOW_GLOBAL_POINTER_FALLBACKS=1 unless the user explicitly requested click_method: "global", a drag that must drive a window-server drag session (window move, drag-select text, Finder drag-and-drop), or other diagnostic behavior that may move the real pointer. Without it drag reports Drag delivered via app_post and those operations have no effect; see references/usage.md for alternatives.
  • On Windows and Linux, confirm the command is running inside the logged-in desktop session before assuming GUI automation is available.

Common CLI Actions

open-computer-use -h
ocu -h
ocu capabilities --json
ocu js 'nodeRepl.write(6 * 7)'
ocu repl
open-computer-use doctor
open-computer-use call list_apps
ocu call list_apps
open-computer-use call get_app_state --args '{"app":"TextEdit"}'
open-computer-use call get_app_state --args '{"app":"TextEdit","text_limit":1000}'
open-computer-use call get_app_state --args '{"app":"TextEdit","text_limit":"max"}'
open-computer-use call get_app_state --args '{"app":"Google Chrome","max_tree_nodes":3000,"max_tree_depth":96}'
open-computer-use call click --args '{"app":"TextEdit","element_index":"0"}'
open-computer-use call type_text --args '{"app":"TextEdit","text":"Hello from Open Computer Use"}'

For a short sequence that reuses state in one process:

open-computer-use call --calls '[
  {"tool":"get_app_state","args":{"app":"TextEdit"}},
  {"tool":"press_key","args":{"app":"TextEdit","key":"Return"}}
]'

MCP Usage

For runtimes that can launch local MCP servers over stdio, use:

[mcp_servers.open_computer_use]
command = "open-computer-use"
args = ["mcp"]

Read references/usage.md for JSON config examples, direct tool-call patterns, and platform notes.

References