Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Clara Windows UI MCP List all open windows and focus the game window"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Local-only MCP server for Windows UI automation oriented toward difficult targets such as game windows, legacy desktop apps, and surfaces that do not expose UI Automation reliably.
The built-in computer-use flow is convenient, but it can struggle with windows that render through game engines or custom graphics pipelines. This MCP takes a lower-level path:
enumerate and focus windows through HWND
drive mouse and keyboard input through native Win32 APIs
capture the desktop or a target window to PNG files
expose the same behavior through MCP stdio and a small local HTTP API
Related MCP server: OmniFlow
list_windows
get_foreground_window
focus_window
capture_screen
move_mouse
click_mouse
press_key
type_text
The src/domain/vision module defines the shared, consumer-facing vision contract:
SceneObservation carries capture provenance, OCR, and detection results.
SceneEvent leaves room for optional temporal change notifications.
VisionProfileRegistry isolates examples, training-set references, and rules by applicationId.
Capture and detection implementations are intentionally not part of this foundation. Consumers should depend on the scene/event contract rather than detector internals.
The native projects use the same safe session boundary as the Clara Cursor:
ClaraVisionBroker Windows service -> local named pipe -> ClaraVisionTray user-session agentThe broker persists the high-level observation state (paused or
observing) and relays it locally.
The tray shows that state and lets the user start or pause observation.
Neither component captures the desktop or performs automation. A future session agent will connect the existing opt-in capture pipeline only after a target selection and capture policy are defined.
Build native/ClaraVisionBroker and native/ClaraVisionTray in Release. Then
run scripts/install-vision-service.cmd from an elevated Command Prompt and
scripts/install-vision-tray.cmd from the interactive user session.
npm.cmd install
npm.cmd run build
npm.cmd run start:stdioFor local diagnostics:
npm.cmd run start:apirun mode: stdio, api, or both
deployment profile: local-only
authentication: none
storage: local file output only for captures
organization: CQRS-style commands and queries with transport adapters
Screenshots are written under captures/.
This first version avoids UIA on purpose so it remains useful for games and canvas-rendered apps.
The next logical upgrade is target-aware matching by template image, pixel region, or OCR.
Capture the desktop or a specific window to a PNG file.
Inputs: selector, outputPath.
Click at a screen coordinate using the selected mouse button.
Inputs: x (required), y (required), button (required), doubleClick (required).
Bring a target window to the foreground by HWND or partial title match.
Inputs: handle, titleIncludes.
Get the current foreground window.
Inputs: no named parameters.
List visible top-level windows with HWND, title, process info, bounds, and foreground state.
Inputs: no named parameters.
Move the mouse cursor to an absolute screen coordinate.
Inputs: x (required), y (required).
Send a key sequence through SendKeys syntax, for example {ENTER} or ^a.
Inputs: key (required).
Type text through SendKeys with special characters escaped.
Inputs: text (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 8 tools
Each tool targets a distinct action: listing windows, getting foreground, focusing, capturing, mouse movement/click, and keyboard input. No overlap in purpose, unambiguous.
All tool names follow a consistent verb_noun pattern (list_windows, get_foreground_window, capture_screen, etc.) with snake_case, perfectly predictable.
8 tools is well-scoped for a Windows UI automation server, covering window management, screen capture, and input simulation without bloat or thinning.
The set covers core UI automation workflows (window handling, mouse/keyboard input, screenshot). Minor gaps like reading window properties or mouse scroll are not critical but could be added.
Eyes and hands on real Windows PCs — observe, click, type via Glasswarp API.
Securely control computers you explicitly pair through files, terminals, processes, screenshots, desktop UI/input, clipboard, browser automation, diagnostics, and document tools.
Connect ChatGPT, Claude, Cursor or VS Code to your Windows PC: files, terminal, browser, apps.
Control your authorized Windows computers via OAuth: files, shell, apps, and task status.
