# screenread

> screenread — bambushu-screenread. Use this tool when you need to quickly extract text from a macOS screen for your AI agent to process, eliminating the need for screenshots. ScreenRead solves the problem of text extraction by providing the macOS accessibility tree in approximately 100ms through its CLI and MCP server interface. It takes screen data as input and outputs the extracted text, ideal for use cases requiring fast and accurate text recognition.

Canonical page: https://skillsregistry.net/skills/bambushu-screenread  
JSON: https://api.skillsregistry.net/v1/skills/bambushu-screenread

## Description

Your AI agent doesn't need screenshots to read text. ScreenRead gives it the macOS accessibility tree in ~100ms. CLI + MCP server.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/Bambushu/screenread)

## 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": "bambushu-screenread"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bambushu-screenread` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bambushu-screenread/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