# Ubuntu Desktop Control MCP

> Use this tool when you need to automate interactions with Ubuntu desktop applications, or require AI-driven visual interaction with desktop elements. It solves problems such as automating repetitive tasks, integrating with desktop applications, and enabling AI assistants to interact with graphical user interfaces. The tool takes screenshots and AT-SPI data as inputs and outputs mouse clicks and keyboard interactions to control the desktop.

Canonical page: https://skillsregistry.net/skills/charettep-ubuntu-desktop-control-mcp  
JSON: https://api.skillsregistry.net/v1/skills/charettep-ubuntu-desktop-control-mcp

## Description

Enables AI assistants to control Ubuntu desktops through screenshots, mouse clicks, and keyboard interactions using AT-SPI integration and computer vision. It features optimized element detection and workflow batching for fast and accurate visual interaction with desktop applications.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-02

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/su2egt6k67)
- **Repository:** <https://github.com/charettep/ubuntu-desktop-control-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": "charettep-ubuntu-desktop-control-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/charettep-ubuntu-desktop-control-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/charettep-ubuntu-desktop-control-mcp/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