Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
portNoPort for the HTTP server.
tokenNoFixed bearer token for authentication. If not provided, a random token is generated and printed.
widthNoScales screenshot width and coordinates for the model.
heightNoScales screenshot height and coordinates for the model.
no-tunnelNoDisables the Cloudflare quick tunnel for LAN or SSH-forwarded use.false
allow-filesNoAdds file read, write, and delete tools.false
allow-shellNoAdds the computer_run_command tool (shell access).false

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

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
computer_screenshotA

Capture a screenshot of the current screen.

Returns the current screen state as an image. Always call this first to see what's on screen before performing any actions.

computer_get_screen_sizeA

Get the screen dimensions.

Returns: Dictionary with 'width' and 'height' keys in pixels.

computer_get_cursor_positionA

Get the current cursor position.

Returns: Dictionary with 'x' and 'y' coordinates.

computer_get_desktop_stateA

Capture the whole desktop through the active Cua Driver session.

This tool is available only with CUA_BACKEND=cua-driver. In an auto session, explicitly escalate the capture scope only after the window-focused ladder is exhausted.

computer_clickB

Click at the specified screen coordinates.

computer_double_clickB

Double-click at the specified screen coordinates.

computer_moveA

Move the cursor to the specified screen coordinates.

computer_dragB

Drag from start coordinates to end coordinates.

computer_scrollC

Scroll at the specified position.

computer_mouse_downA

Press and hold a mouse button.

computer_mouse_upC

Release a mouse button.

computer_typeB

Type text at the current cursor position.

computer_press_keyB

Press a single key.

computer_hotkeyB

Press a key combination (hotkey).

computer_key_downC

Press and hold a key.

computer_key_upA

Release a held key.

computer_clipboard_getA

Get the current clipboard content.

Returns: Dictionary with clipboard content.

computer_clipboard_setC

Set the clipboard content.

computer_openA

Open a file or URL with the default application.

computer_launch_appB

Launch an application.

computer_get_active_windowA

Get the currently active window ID.

Returns: Dictionary with 'window_id' key.

computer_get_window_nameA

Get the title/name of a window.

computer_get_window_sizeB

Get the size of a window.

computer_get_window_positionB

Get the position of a window.

computer_set_window_sizeC

Set the size of a window.

computer_set_window_positionB

Set the position of a window.

computer_activate_windowA

Bring a window to the foreground and focus it.

computer_minimize_windowC

Minimize a window.

computer_maximize_windowC

Maximize a window.

computer_close_windowC

Close a window.

computer_get_app_windowsB

Get all windows belonging to an application.

computer_get_desktop_environmentA

Get information about the current desktop environment.

Returns: Dictionary with desktop environment details.

computer_get_accessibility_treeA

Get the accessibility tree of the current window.

This provides detailed information about UI elements that can be useful for finding clickable elements or understanding the UI structure.

Returns: Dictionary with the accessibility tree structure.

computer_find_elementB

Find a UI element in the accessibility tree.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

B3.4/5.0

Scored across 34 tools

Disambiguation4/5

Most tools are clearly distinct (screenshot, click, type, window management), but computer_get_desktop_state overlaps with computer_screenshot, and computer_get_active_window/computer_get_window_name could be confused. The mouse_down/up and key_down/up pairs are distinct but similar in purpose.

Naming Consistency5/5

All tools follow a consistent computer_verb_noun pattern (e.g., computer_get_cursor_position, computer_set_window_size, computer_activate_window). The naming is uniform and predictable across the entire set.

Tool Count4/5

34 tools is on the higher end, but the scope is broad (screen, mouse, keyboard, clipboard, windows, accessibility), so each tool covers a distinct action. It feels slightly heavy but justified for a full computer control server.

Completeness5/5

The tool surface covers the full lifecycle of computer interaction: observation (screenshot, accessibility tree), input (mouse, keyboard, clipboard), window management (get/set/activate/minimize/maximize/close), and app launching. No obvious dead ends for an agent automating a Mac.

Maintenance

ActivityMaintained
ResponsivenessNo issues