# macOS Vision OCR

> Use this tool when you need to extract text from images and PDFs on macOS devices, solving problems such as document digitization and text recognition. It takes images and PDFs in various formats as input and outputs extracted text with confidence scores, using a local processing approach that eliminates the need for API keys. Ideal for use cases requiring on-device text extraction, such as document scanning and image processing applications.

Canonical page: https://skillsregistry.net/skills/br3akzero-vision-ocr  
JSON: https://api.skillsregistry.net/v1/skills/br3akzero-vision-ocr

## Description

A native macOS MCP server using Apple Vision Framework for on-device text extraction from PDFs and images. Provides two tools: structured PDF OCR via RecognizeDocumentsRequest and image OCR via VNRecognizeTextRequest. Supports PNG, JPEG, TIFF, HEIC, and WebP formats with confidence scores and automatic text chunking. All processing is fully local with no API keys required.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/br3akzero-vision-ocr)
- **Repository:** <https://github.com/br3akzero/vision.mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "br3akzero-vision-ocr"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/br3akzero-vision-ocr` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/br3akzero-vision-ocr/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt