codex-computer-use-linux
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| desktop_statusA | Call first to detect Wayland or X11, screenshot and input backends, the active window, and safety warnings. This does not capture the screen or send input. |
| take_screenshotA | Capture the current Linux desktop as PNG image content. Use before choosing coordinates and again after every action that changes visible state. |
| move_pointerA | Move the pointer to absolute coordinates from the latest screenshot. |
| clickA | Move to absolute screenshot coordinates and click a mouse button. Use one click unless the visible control clearly requires a double-click. |
| drag_pointerA | Drag a mouse button between two absolute coordinates from the latest screenshot. |
| type_textA | Type bounded plain text into the currently focused control. Never pass passwords, tokens, recovery codes, payment data, or terminal commands. |
| press_keyA | Press one allow-listed key with optional ctrl, alt, shift, or super modifiers in the focused Linux app. |
| scrollA | Scroll vertically by a small number of steps. Positive scrolls up and negative scrolls down. On Wayland use press_key with PAGEUP or PAGEDOWN instead. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Each tool targets a distinct action: status inspection, screenshot capture, pointer movement, clicking, dragging, typing, key pressing, and scrolling. No two tools have overlapping purposes; even move_pointer and click are clearly differentiated by the act of clicking.
Most tools follow a verb_noun pattern (take_screenshot, move_pointer, drag_pointer, type_text, press_key), but 'click' is a bare verb and 'desktop_status' is a noun phrase. This inconsistency in naming style is noticeable but still readable.
Eight tools cover the essential actions for computer use on Linux without being excessive. Each tool serves a distinct purpose, and the count is well within the ideal 3-15 range.
The surface covers the core actions: observing the screen, moving the pointer, clicking, dragging, typing, pressing keys, and scrolling. Minor gaps exist, such as no explicit method to retrieve the current cursor position or handle clipboard, but these are not critical for the primary purpose.