MCP server directory

macos-vision-mcp

Local OCR and on-device screen reading for MCP clients (Claude, Cursor): read any window, locate elements to click, assert what's on screen. Apple Vision, no API keys, nothing uploaded.

Provides local, private, offline OCR and UI testing for Mac, enabling agents to see and interact with the UI without sending screenshots or sensitive data off the machine, significantly reducing token costs and enhancing privacy.

Version:: 0.7.0
Publisher:: GitHub Actions
Company:: woladi (third-party)
Docs:: raw.githubusercontent.com/woladi/macos-vision-mcp/HEAD/README.md; Summary written by google/gemini-2.5-flash-lite from the server’s own site and README; facts above come from the registries.; Logo: https://raw.githubusercontent.com/woladi/macos-vision-mcp/master/.github/assets/logo-128.png

Install

Generated from the server’s transport data — never hand-written. Placeholders in angle brackets are yours to fill.

Run it with its own identity, a budget you set, and every call audited — no local config to keep in sync.

Add to a connect0 project

You will sign in first, then land back on this page.

What it can do

No capability summary yet — the publisher has not declared one and it has not been verified.