What it does
The publisher describes this MCP server as providing local OCR and screen understanding for agents. It can read any window and help an agent find what to click, and the description states that it involves no uploads.
It fits workflows where an agent needs to read on-screen text or locate interface elements on a Mac without sending screen content elsewhere. The source does not describe setup steps or requirements beyond the repository linked on this page.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.woladi/macos-vision-mcp
Local OCR & screen understanding for agents: read any window, find what to click. No uploads.
v0.7.0As shown on registry.modelcontextprotocol.io when we last read it