som-window-mcp
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.
Read-only access to Windows desktop windows.
Typical flow:
list_windows -> pick a window, get its hwnd.
get_ui_tree(hwnd) -> compact list of buttons, edits, tabs with screen rects.
capture_window(hwnd) -> pixels of that window only, even if it is covered.
capture_som(hwnd) -> the same capture with numbered boxes on every control, for when you need to locate something visually or in a dense layout.
Nothing here clicks, types or moves the mouse. Coordinate space is physical screen pixels, and captures report the screen position of image pixel (0,0).
Known limits: elevated windows need an elevated server; Chromium/Electron apps expose no UI tree unless started with --force-renderer-accessibility (screenshots still work); minimised windows and some GPU surfaces capture blank.
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_windowsA | List visible top-level windows, foreground first. |
| get_ui_treeA | Read the UI Automation tree of one window as a compact text list. |
| inspect_elementA | Read the full content of one element, identified by a path. |
| capture_windowA | Capture one window's pixels, including while it is covered. |
| capture_somA | Capture a window with numbered marks on every interactive element. |
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 5 tools
The five tools target distinct stages of window inspection, but there is some inherent overlap: get_ui_tree and inspect_element both read the UIA tree at different granularities, and capture_window and capture_som both return screenshots. The descriptions explicitly clarify when to use the marked capture or element-level inspection, so an agent can usually choose correctly.
All tool names use consistent snake_case with clear verb_noun forms: list_windows, get_ui_tree, inspect_element, capture_window, capture_som. The verbs are predictable and the nouns identify the resource or output type.
Five tools is well-scoped for a focused window-inspection server. Each tool covers a distinct capability: enumeration, tree reading, element detail, plain capture, and marked capture.
The surface covers the read-only inspection lifecycle well: list windows, inspect their UI trees, drill into elements, and capture plain or marked images. The main gap is the absence of any interaction or action tools such as clicking or typing, which an agent may expect from a window-automation server.