# OmniParser AutoGUI

> Use this tool when you need to automate interactions with graphical user interfaces or analyze on-screen GUI elements. The OmniParser AutoGUI server solves problems related to automated testing, accessibility assistance, and programmatic control of desktop applications. It takes visual inputs from the screen and outputs automated GUI interactions, making it ideal for tasks that require AI-assisted control of visual interfaces.

Canonical page: https://skillsregistry.net/skills/non906-omniparser-autogui  
JSON: https://api.skillsregistry.net/v1/skills/non906-omniparser-autogui

## Description

This MCP server analyzes on-screen GUI elements using OmniParser and enables automated GUI interactions. Developed by NON906, it integrates computer vision and automation libraries to provide AI-assisted control of desktop applications. The server is particularly useful for tasks requiring visual analysis and programmatic interaction with graphical user interfaces, such as automated testing or accessibility assistance.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/non906-omniparser-autogui)
- **Repository:** <https://github.com/non906/omniparser-autogui-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": "non906-omniparser-autogui"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/non906-omniparser-autogui` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/non906-omniparser-autogui/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