mcp-macos-cua
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| screenshotA | Take a screenshot of the entire screen or a specific app window. Returns the image and the display scale factor (divide screenshot pixel coordinates by this factor to get tool coordinates). |
| open_appB | Open and activate a macOS application |
| clickA | Click at screen coordinates (in points). Use screenshot to determine positions — on Retina displays, divide screenshot pixel coordinates by 2. |
| type_textB | Type text using the keyboard. The frontmost app receives the input. |
| key_pressA | Press a key or key combination (e.g. 'return', 'escape', 'cmd+c', 'cmd+shift+l') |
| scrollC | Scroll at the current mouse position or at given coordinates |
| get_ui_elementsB | Get accessibility UI elements of a window for a given app. Useful for finding buttons, text fields, etc. |
| click_ui_elementC | Click a named UI element (button, menu item, etc.) within an app window using accessibility |
| run_applescriptA | Run arbitrary AppleScript for complex automation that other tools don't cover |
| get_mouse_positionA | Get the current mouse cursor position in screen points |
| move_mouseC | Move mouse cursor to given screen coordinates |
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 11 tools
Each tool has a clearly distinct purpose. Even overlapping tools like click and click_ui_element are differentiated by coordinate-based vs accessibility-based interaction.
All tool names follow a consistent verb_noun pattern with underscores (e.g., type_text, get_ui_elements). No mixed conventions.
11 tools is well-scoped for macOS UI automation, covering common actions without being overwhelming.
Covers core operations (typing, clicking, scrolling, screenshots, app opening, accessibility, AppleScript). Minor gaps like window management or drag-and-drop, but strong overall.