ocr_screen_structured

MCP tool from Win32 MCP Server by RandyNorthrup

Full screen OCR with bounding boxes

How to use it

Project documentation lists ocr_screen_structured for the Win32 MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.

Install Win32 MCP Server

$win32-mcp-server
FULL WIN32 MCP SERVER LISTING

Other tools in Win32 MCP Server (39)

assert_text_visible

Verify text is or is not visible (for UI testing)

capture_monitor

Capture specific monitor by index

capture_screen

Full screen screenshot (PNG/JPEG/WebP)

capture_window

Window screenshot with fuzzy title match

click

Click at coordinates (left/right/middle, N clicks)

click_text

Find text on screen and click it — no coordinates needed

clipboard_copy

Copy text to clipboard

clipboard_paste

Read clipboard contents

compare_screenshots

Pixel-level comparison with similarity score

double_click

Double-click at coordinates

drag

Drag from start to end with duration

execute_sequence

Run up to 50 tools in sequence without round-trips

fill_field

Click a labeled input field and type a value

find_text_on_screen

Locate all occurrences of text with screen coordinates

get_pixel_color

Get RGB/hex color at coordinates

get_window_snapshot

Screenshot + structured OCR in one call

health_check

verify all dependencies, DPI, monitors, Tesseract, and tool count

hotkey

Hotkey from key array (["ctrl","shift","s"])

list_monitors

List monitors with resolution and DPI

list_windows

List windows with optional title filter

mouse_move

Move cursor with smooth animation

mouse_position

Get current cursor position

ocr_region

Region text extraction

ocr_region_structured

Region OCR with bounding boxes

ocr_screen

Full screen text extraction

ocr_window

Window text extraction

press_key

Press key or combo (ctrl+c, alt+f4)

right_click_menu

Right-click and OCR the context menu items

scroll

Vertical scroll at position

scroll_horizontal

Horizontal scroll at position

triple_click

Triple-click to select line/paragraph

type_text

Type text (auto Unicode detection, clipboard fallback)

uia_click_control

click a control by name (more reliable than coordinates)

uia_find_control

find controls by type, name, or automation ID

uia_get_control_value

read a control's value or text

uia_get_focused

get info about the currently focused control

uia_inspect_window

get the control tree of a window

uia_set_control_value

set a control's value (edit boxes, etc.)

wait_for_text

Poll until text appears on screen (with timeout)