# Screen Vision MCP Server

> Use this tool when you need to capture and analyze visual data from your screen, such as text extraction via OCR or real-time screen monitoring. It solves problems like automated text recognition, screen recording, and video analysis, providing outputs like extracted text and analyzed video data. The tool runs locally as an MCP server, accepting inputs like screen feeds and video files, and is ideal for use cases requiring local data processing and analysis.

Canonical page: https://skillsregistry.net/skills/avicuna-screen-vision  
JSON: https://api.skillsregistry.net/v1/skills/avicuna-screen-vision

## Description

Enables Claude to capture screenshots, watch your screen in real-time, read text via OCR, and analyze video files, all running locally as an MCP server.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/uaduj84tgc)
- **Repository:** <https://github.com/avicuna/screen-vision>

## 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": "avicuna-screen-vision"
    }
  }
}
```

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