take_screenshotLABSCO SUMMARY
Reads the UI tree instead of guessing from a screenshot.
Click targets come from Windows UI Automation, so a tap lands on the control rather than near it, and most steps return text instead of an image. The trade is platform: this runs on Windows x64 only.
What it is
A single-binary MCP server for automated desktop UI testing on Windows. It gives an agent the screen, the window list, the Windows UI Automation tree and OCR, plus mouse and keyboard control.
What you get
- Full-screen and single-window screenshots (take_screenshot, take_window_screenshot)
- The actual UI structure, with roles, states and coordinates read through Windows APIs rather than estimated from a picture (list_ui_elements)
- Window enumeration and focus (list_windows, focus_window)
- Mouse click, move, drag and scroll at exact coordinates (mouse_click, mouse_move, mouse_drag, mouse_scroll)
- Typed text, single key presses and shortcut combinations (keyboard_type, keyboard_press, keyboard_shortcut)
- OCR with word-level coordinates, over the whole screen or one region (read_screen_text, read_region_text)
Requirements
Windows x64; macOS and Linux are listed as planned. One binary, with no runtime and no dependencies to install.
Setup effort
Follow the published steps
USE CASES
01
Checking a desktop app did what the agent asked
Trigger the action, capture the screen and read the result back as text.
02
Clicking a control precisely
List the UI elements to get the control's coordinates, then click there.
03
Filling in a form end to end
Bring the window forward, type into the fields and send the shortcut that submits.
04
Reading text the app draws but does not expose
Run OCR over one region and get the words back with their coordinates.
05
Working across several open windows
List what is open, bring the right window forward and capture only that window.
19 tools
Listed in project docs. Your client may show a different list.
take_window_screenshotread_screen_textread_region_textlist_windowsfocus_windowmouse_clickmouse_movemouse_dragmouse_scrollkeyboard_typekeyboard_presskeyboard_shortcutlist_ui_elementssearch_in_filesfind_filesget_usage_guideenable_loggingdisable_loggingBEFORE YOU INSTALL
What to know first
Tools you get
19 tools named in the project's documentation.
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
Download mcp-test-utils.exe from the project's Releases page: https://github.com/JeenyJAI/mcp-test-utils/releases (Windows x64 only)
Add it to your MCP client config, with command set to the full path where you saved the .exe. For Claude Desktop the file is %APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"test-utils": {
"command": "<YOUR_PATH_TO_MCP_TEST_UTILS>"
}
}
}<YOUR_PATH_TO_MCP_TEST_UTILS> is the full path of the binary you downloaded from Releases.
