FRENES

Image, video and audio · MCP server

Macos vision MCP: MCP server, setup and security

Macos vision MCP is an open-source MCP server that lets an AI agent extract text and detect faces barcodes and QR codes offline. Its repository has 7 stars and its last commit is from August 25, 2026 and it is licensed under MIT.

Actively maintained

What Macos vision MCP does

According to its repository: “Offline OCR and image analysis via Apple's Vision framework: text from images and PDFs with bounding boxes, face, barcode and QR detection, and classification.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Macos vision MCP is listed under Image, video and audio, a category of 67 servers in the directory, where it ranks #56 by stars.

Topics declared by the repository: apple-vision, claude-code, macos, ocr, offline.

Installing and connecting Macos vision MCP

Distribution modes declared in the official MCP registry:

  • npm package (Node.js, usually started with npx)

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: TypeScript. Listed systems: macOS.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

None of the risk signals we track (system access, secrets, missing licence, abandonment) applies to Macos vision MCP. That does not replace reading the code.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on April 9, 2026, the woladi/macos-vision-mcp repository has 7 stars and 0 forks, with 0 open issues. It has more stars than 19% of the servers in the directory. Last change 2 months ago. Version published in the registry: 0.7.0 (August 25, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

ScreenpipeScreenpipe : 22.1K22.1KFunASRFunASR : 20.8K20.8KRemove AI WatermarksRemove AI Watermarks : 6.1K6.1KOpenScreenOpenScreen : 4.9K4.9KOpenPostOpenPost : 755755FableCutFableCut : 746746Anki MCP ServerAnki MCP Server : 531531MCP youtube transcriptMCP youtube transcript : 492492Macos vision MCPMacos vision MCP : 77
GitHub stars of the most followed servers in the category (log scale); Macos vision MCP in orange. Checked October 25, 2026.

Verdict

Macos vision MCP is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Limitations

  • Few visible users

Frequently asked questions

How do I install Macos vision MCP?

Macos vision MCP is distributed as npm package (Node.js, usually started with npx). Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of woladi/macos-vision-mcp.

Is Macos vision MCP free?

The code is published under the MIT licence and can be used free of charge.

Is Macos vision MCP safe?

No risk signal found (system access, secrets, licence, abandonment). As with any MCP server, keep rights minimal and read the code before sensitive use.

Is it an official server?

Nothing says so: it is a project published by woladi on GitHub. Check who maintains it before giving it access.

What are the alternatives to Macos vision MCP?

In the same category: OpenScreen, Remove AI Watermarks, FunASR, and Oh My Cassette. OpenScreen and Remove AI Watermarks score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score