macOS GUI Control MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TIMEOUT | No | Command timeout (ms) | 30000 |
| LOG_OPERATIONS | No | Operation log output | true |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| mouse_clickC | Left-click at screen coordinates |
| mouse_double_clickC | Double-click at coordinates |
| mouse_right_clickC | Right-click at coordinates |
| mouse_moveB | Move cursor to position (without clicking) |
| mouse_dragC | Drag from point A to point B |
| mouse_scrollC | Scroll in a direction |
| mouse_get_positionB | Get current cursor position |
| keyboard_typeC | Type text at current cursor position |
| keyboard_pressB | Press a key or key combination (e.g., 'enter', 'cmd+c', 'shift+tab') |
| keyboard_shortcutC | Execute common keyboard shortcut |
| screen_captureC | Take a screenshot (full screen or region) |
| screen_get_sizeB | Get main screen dimensions |
| screen_get_colorC | Get pixel color at coordinates |
| window_listB | List all visible windows |
| window_focusC | Focus/activate an application |
| window_moveC | Move application window to position |
| window_resizeC | Resize application window |
| run_applescriptA | Run arbitrary AppleScript code (full power, deletion blocked) |
| run_shellB | Run shell command (full power, deletion blocked) |
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 19 tools
Every tool has a clearly distinct purpose with no ambiguity. The tools are organized into logical categories (keyboard, mouse, screen, window, execution), and even within categories like mouse operations, each tool performs a specific, non-overlapping action (click, double-click, drag, move, etc.).
Tool names follow a consistent verb_noun pattern throughout (e.g., keyboard_press, mouse_click, screen_capture, window_list). All names use snake_case consistently, and verbs are appropriately descriptive for their actions, making the set highly predictable and readable.
With 19 tools, this is well-scoped for macOS GUI control, covering input (keyboard, mouse), output (screen), window management, and execution (AppleScript, shell). Each tool earns its place by addressing a specific aspect of GUI automation without redundancy, making the count appropriate for the domain.
The tool surface provides complete coverage for macOS GUI control, including input simulation (keyboard and mouse actions), screen interaction (capture, color, size), window management (list, focus, move, resize), and execution capabilities (AppleScript, shell). There are no obvious gaps, and agents can perform comprehensive GUI automation tasks without dead ends.