ocr

MCP tool from Nova by bigduu

Recognize on-screen text via Apple Vision (on-device, no model files). Returns each text line with a clickable center — read and click text on canvas/Electron/game surfaces where marks are empty. CJK + Latin.

How to use it

ocr is exposed by the Nova MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the ocr tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.

Install Nova

$npx -y @bigduu/nova --version

FULL NOVA LISTING

Other tools in Nova (8)

ax_activate

Activate an exact actionable node from a fresh axread; rejects stale snapshot IDs and reports route=ax\

ax_read

Canonical ax:read: read semantic labels, text, values, roles, actions, state, and optional bounds through macOS Accessibility or Windows UIA, without a screenshot. Returns an ephemeral snapshot/node protocol and explicit coverage/status.

batch_actions

Run a sequence of input actions in one call.

click_mark

Compatibility action for the latest numbered mark; prefer generation-safe axactivate.

read_ui

Compatibility alias backed by the same axread traversal and cache generation.

screenshot

Capture the whole display or a single window= — use for layout, icons, colors, images, canvas, and visual verification after semantic/OCR paths.

wait

Pause for a specified number of seconds.

zoom_region

Magnify a rectangle of the last screenshot at native resolution — reads small targets on surfaces with no Accessibility tree.