Skip to main content
Glama
codex-cua-mcp

codex-cua-mcp

by RS-Nocsi

Codex CUA MCP

δΈ­ζ–‡η‰ˆ

πŸ’¬ LINUX DO Discussion

Wraps Codex's Computer Use capability as an MCP server, enabling AI agents to control Windows desktop applications.

Features

  • List and control Windows desktop applications

  • Capture screenshots and accessibility trees

  • Click, type, press keys, scroll, drag, and more

  • Launch apps and activate windows

  • Ready to use - exe bundled, no extra setup needed

Related MCP server: Windows-MCP

Quick Start

Hand the install doc to your AI agent β€” send this prompt:

Please clone the repository https://github.com/RS-Nocsi/codex-cua-mcp locally, read its INSTALL.md, and install this MCP server into your own MCP configuration by following it.

Your agent (Claude Code, Cursor, Windsurf, Cline, OpenCode, Gemini CLI, etc.) will clone the repo, check prerequisites, build the project, and register the server itself. Fully restart the agent afterwards.

Prefer manual setup? Follow INSTALL.md yourself.

How It Works

AI Agent (Claude Code, Cursor, etc.)
  ↓ MCP protocol (stdio)
MCP Server (codex-cua-mcp)
  ↓ JSON-RPC (stdin/stdout)
codex-computer-use.exe
  ↓ Windows APIs
Desktop Applications

The MCP server communicates with codex-computer-use.exe via JSON-RPC over stdin/stdout. The exe uses Windows APIs (SendInput, UI Automation, Windows.Graphics.Capture) to interact with desktop applications.

Dynamic agent name

The desktop overlay shows which agent is controlling the computer (e.g. "Claude Code is using your computer"). Please set the CUA_AGENT_NAME environment variable to your own display name in the registration β€” see INSTALL.md Step 4. Each agent has its own runtime config under config-runtime/; multiple agents can install this MCP simultaneously without conflict.

πŸ“– Want to understand the design in depth? Read the Architecture Deep Dive.

Available Tools

Tool

Description

list_windows

List all controllable windows

list_apps

List installed apps

get_window

Rehydrate a window object

launch_app

Launch an application

activate_window

Bring window to foreground

get_window_state

Screenshot + accessibility tree

click

Click

type_text

Type text

press_key

Press key

scroll

Scroll

drag

Drag

set_value

Set input field value

perform_secondary_action

Secondary action (right-click menu, etc.)

Disclaimer

The core capability comes from codex-computer-use.exe. Actual results depend on the AI agent and model used β€” no usability guarantee.

Requirements

  • Windows 10/11

  • Node.js 18+

License

MIT

Available Tools

13 tools
activate_windowC

Bring a window to the foreground

Inputs: window (required).

clickC

Click at coordinates or on an element in a window

Inputs: window (required), x, y, click_count, +3 more.

dragC

Drag from one coordinate to another in a window

Inputs: to_x (required), to_y (required), from_x (required), from_y (required), +2 more.

get_windowB

Rehydrate a window object by id (useful after losing window binding)

Inputs: id (required), app.

get_window_stateA

Capture screenshot and/or accessibility tree of a window. Call this before input actions.

Inputs: window (required), include_text, include_screenshot.

launch_appC

Launch an application

Inputs: app (required).

list_appsA

List installed apps with their open windows

Inputs: no named parameters.

list_windowsB

List all open windows that can be controlled

Inputs: no named parameters.

perform_secondary_actionC

Perform a secondary action on an element (e.g., right-click menu, expand)

Inputs: action (required), window (required), element_index (required).

press_keyB

Press a keyboard key or chord (e.g., 'Return', 'Control_L+a')

Inputs: key (required), window (required).

scrollC

Scroll at coordinates in a window

Inputs: x (required), y (required), window (required), scrollX (required), +2 more.

set_valueC

Set the value of an editable element

Inputs: value (required), window (required), element_index (required).

type_textC

Type text into the current focus of a window

Inputs: text (required), window (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 13 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: window management, input actions, app launching, and element manipulation. No two tools overlap in functionality.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with underscores (e.g., activate_window, get_window_state). No mixing of styles or irregular naming.

    Tool Count5/5

    13 tools cover a well-scoped set of GUI automation operations (window control, input, app management), neither too few nor excessive for the domain.

    Completeness4/5

    The tool surface covers core actions (launch, list, navigate, input, state capture). Minor gaps like explicit screenshot-only or element waiting could exist but the set is largely complete for typical workflows.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to interact with Windows operating systems through native UI automation, file navigation, application control, and system commands. Provides seamless integration between LLMs and Windows environments for tasks like clicking, typing, launching apps, and capturing desktop state.
      MIT