codex-computer-use-linux
Provides Linux desktop automation capabilities, including taking screenshots, moving and clicking the mouse, typing text, pressing keys, dragging, and scrolling within the Linux graphical session.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@codex-computer-use-linuxTake a screenshot and verify the login form is displayed."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Codex Computer Use for Linux is an open-source Linux computer-use MCP server and Codex skill for controlled desktop GUI automation. It gives Codex a deliberately small tool surface for working with visible native applications while keeping sensitive workflows out of scope.
This is an independent community project. It is not made, supported, or endorsed by OpenAI and does not claim feature parity with OpenAI Computer Use.
OpenAI's current Computer Use plugin supports macOS and Windows, while Codex can connect to local STDIO MCP servers. This project fills the Linux integration gap with an MCP action layer and a skill that teaches Codex the safe observe → act → verify loop. See the official Computer Use and MCP documentation for the product boundaries.
Why MCP plus a skill?
Layer | Responsibility |
MCP server | Executes typed, bounded Linux desktop actions and reports capability errors. |
Codex skill | Chooses safe action sequences, verifies UI state, and stops on sensitive flows. |
Plugin | Packages the skill and MCP connection for repeatable installation. |
A skill alone cannot reliably provide live screenshots or controlled input. An MCP server alone does not teach the model a safe visual workflow. The hybrid plugin follows OpenAI's documented plugin architecture.
Related MCP server: desk-mcp
What it does
Linux-only runtime guard; no silent macOS or Windows fallback.
Wayland input through
ydotool; X11 input throughxdotoolwithydotoolfallback.Screenshots through
grim,gnome-screenshot,scrot, or ImageMagickimport.Typed MCP tools for status, screenshot, pointer movement, click, drag, text, keys, and scroll.
No arbitrary shell tool, application launcher, clipboard reader, or secret store access.
Best-effort blocking of terminals, ChatGPT, and Codex when the active window is discoverable.
Structured Doctor output and in-memory MCP contract tests.
Installable Codex plugin plus direct MCP-server setup.
Quick start
Requirements
Linux with an active graphical session.
Python 3.11 or newer.
One screenshot backend.
One input backend.
Session | Screenshot | Input | Notes |
Wayland |
|
|
|
X11 |
|
|
|
Install only the packages relevant to your desktop. Typical package names are:
# Debian / Ubuntu
sudo apt install python3 python3-venv xdotool gnome-screenshot ydotool grim
# Fedora
sudo dnf install python3 xdotool gnome-screenshot ydotool grim
# Arch Linux
sudo pacman -S python xdotool gnome-screenshot ydotool grimPackage availability differs by distribution and desktop environment. On Wayland, configure and
start ydotoold according to your distribution. The upstream
ydotool documentation explains its /dev/uinput
permission model; do not run Codex itself as root.
Install
Install the server CLI with one of these isolated Python tool managers:
uv tool install git+https://github.com/maxionice/codex-computer-use-linux.gitor:
pipx install git+https://github.com/maxionice/codex-computer-use-linux.gitRun the Doctor before connecting Codex:
codex-computer-use-linux --doctorOption A: install the Codex plugin
codex plugin marketplace add maxionice/codex-computer-use-linux
codex plugin add codex-computer-use-linux@maxionice-linux-toolsStart a new Codex thread after installing so the skill and MCP tools are loaded.
Option B: add only the MCP server
codex mcp add linux-desktop -- codex-computer-use-linux
codex mcp listFor approval on input-producing tools, configure default_tools_approval_mode = "writes" for the
server in ~/.codex/config.toml.
Example prompts
Use $use-linux-desktop to open the app's settings and verify that dark mode works.Inspect the visible calculator app, enter 125 * 8, and report the displayed result.Reproduce the onboarding bug in the already-open Linux app. Stop before any login prompt.MCP tools
Tool | Effect |
| Reports session, available backends, active window, and warnings. |
| Returns the current desktop as PNG image content. |
| Moves the pointer to absolute screenshot coordinates. |
| Moves and clicks left, middle, or right. |
| Drags between two absolute coordinates. |
| Types bounded plain text into the focused control. |
| Presses a named key with optional modifiers. |
| Scrolls on X11; Wayland users can use Page Up/Down through |
The server never accepts a command string or invokes a shell. Every native command is constructed from validated typed arguments.
Safety model
Desktop automation can act with your logged-in user's permissions and screenshots may contain sensitive data. Keep the target app visible, close unrelated sensitive apps, and review every approval prompt.
The bundled skill refuses terminal, ChatGPT, Codex, credential, administrator, security, payment, and privacy-setting flows. Active-window blocking is best effort because some Wayland compositors do not expose the focused application. Read the complete safety model before use.
Development
git clone https://github.com/maxionice/codex-computer-use-linux.git
cd codex-computer-use-linux
python -m venv .venv
. .venv/bin/activate
python -m pip install -e '.[dev]'
python -m ruff format --check .
python -m ruff check .
python -m mypy src
python -m pytestThe project uses the stable MCP Python SDK 2.x, which supports the 2026-07-28 MCP specification. See the official MCP Python SDK.
Uninstall and rollback
codex plugin remove codex-computer-use-linux
codex plugin marketplace remove maxionice-linux-tools
codex mcp remove linux-desktop
uv tool uninstall codex-computer-use-linuxIf you installed with pipx, replace the final command with
pipx uninstall codex-computer-use-linux. Removing the plugin or MCP entry stops Codex from
launching the server; removing the tool installation deletes the local executable. System packages
such as ydotool are not removed automatically.
Trademark and affiliation
This is an independent open-source project and is not affiliated with or endorsed by OpenAI. OpenAI, Codex, ChatGPT, and related marks belong to their respective owners.
License
Apache-2.0. See LICENSE.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityDmaintenanceProvides automated GUI testing and control capabilities through an MCP server that enables mouse movements, keyboard input, screen captures, and image recognition across Windows, macOS, and Linux.Last updated46MIT
- Alicense-qualityDmaintenanceA desktop automation MCP server that enables AI agents to interact with Linux environments through screenshots, window inspection, and input simulation. It provides tools for mouse control, keyboard input, and screen capture using xdotool and XDG Desktop Portals.Last updatedMIT
- Alicense-qualityAmaintenanceSmall MCP server for GNOME Wayland desktop automation, enabling element lookup, activation, typing, screenshots, and wait helpers through AT-SPI and Mutter RemoteDesktop.Last updated1MIT
- Alicense-qualityAmaintenanceControls a real Linux desktop from any MCP host. Reads accessibility trees, takes screenshots, and drives clicks, scrolls, and keystrokes across GNOME, KDE/KWin, Hyprland, i3, and COSMIC.Last updated254331MIT
Related MCP Connectors
Hosted real Google Chrome MCP with per-user persistent state. Navigate, click, type, screenshot.
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
Access Kernel's cloud-based browsers and app actions via MCP (remote HTTP + OAuth).
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/maxionice/codex-computer-use-linux'
If you have feedback or need assistance with the MCP directory API, please join our Discord server