Is io.github.woladi/macos-vision-mcp safe to use?

io.github.woladi/macos-vision-mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments.

How do I install io.github.woladi/macos-vision-mcp?

io.github.woladi/macos-vision-mcp can be installed by cloning its GitHub repository and following the setup instructions in the README.

What AI clients work with io.github.woladi/macos-vision-mcp?

io.github.woladi/macos-vision-mcp is compatible with Claude Desktop, Cursor, Claude Code, and most MCP clients that support stdio transport. It uses stdio transport.

Is io.github.woladi/macos-vision-mcp actively maintained?

io.github.woladi/macos-vision-mcp is actively maintained — last commit was 0 days ago.

macos-vision-mcp

Local OCR & image analysis for any MCP client — private, offline, no API keys.

Pre-extracts text and image data locally before your AI ever sees it — cutting token usage by ~97% on real documents. Files never leave your Mac: no cloud API, no API keys, no network requests.

What you get

OCR for images and PDFs (JPG, PNG, HEIC, TIFF, multi-page PDF) via Apple Vision Framework.
~97% token reduction: a 44-page PDF costs ~2,400 tokens instead of ~73,500.
Face detection, barcode/QR reading, and image classification — all on-device.
Full document pipeline: OCR + faces + barcodes + rectangles in a single tool call.
Works with Claude Code, Claude Desktop, and Cursor — any MCP-compatible client.
No files uploaded to any server — processing stays entirely on your Mac.
100% offline after npm install — powered by Apple Vision Framework, same engine as Live Text in Photos.app.

❌ Without / ✅ With

❌ Without macos-vision-mcp:

Sending a 44-page PDF costs ~73,500 tokens
Every image, invoice, or contract goes through a cloud API
Sensitive documents leave your machine on every request

✅ With macos-vision-mcp:

Local Apple Vision pre-extracts text before Claude ever sees it
~2,400 tokens for the same 44-page PDF — 97% fewer
Files never leave your Mac

Privacy layer

macos-vision-mcp acts as a local pre-processing layer between your documents and the cloud. Useful for:

Legal documents, contracts, NDAs
Financial reports, invoices, internal spreadsheets
Medical records or any GDPR-sensitive content
Any situation where you want to extract structured data locally before deciding what (if anything) to send upstream

Instead of sending the raw document to your AI, you extract the text and structure locally first. The model then works only with the extracted text — never the original file.

Quick Start

Step 1 — Install the package:

npm install -g macos-vision-mcp

Step 2 — Add to your MCP client (example for Claude Code):

claude mcp add macos-vision-mcp -- macos-vision-mcp

Restart your client. The tools appear automatically.

Note: The native module macos-vision compiles against your local Node.js at install time. If you switch Node versions, run npm rebuild inside the package directory.

Available Tools

Tool	What it does	Example prompt
`ocr_image`	Extract text from an image or PDF (JPG, PNG, HEIC, TIFF, PDF). Returns plain text or structured blocks with bounding boxes.	"Read the text from ~/Desktop/screenshot.png"
`detect_faces`	Detect human faces and return their count and positions.	"How many people are in this photo?"
`detect_barcodes`	Read QR codes, EAN, UPC, Code128, PDF417, Aztec, and other 1D/2D codes.	"What does the QR code in /tmp/qr.jpg say?"
`classify_image`	Classify image content into 1000+ categories wi

... View full README on GitHub

io.github.woladi/macos-vision-mcp

Quick Install

Should you use this server?

Test This Server

Score Breakdown

MCPpedia Score

Security

Help improve this page

Reviews

Frequently Asked Questions

Similar servers

Memory MCP Server

Context Mode

Idea Reality MCP Server

Browser Tools Mcp

Discussion