# Open Computer Use

> Use this tool when you need to automate computer tasks across multiple operating systems, including macOS, Linux, and Windows, using accessibility-based APIs. It solves problems of proprietary screen capture solutions and integrates with various AI agents and MCP clients, such as Codex CLI and Gemini CLI. The tool takes in AI agent commands as input and outputs automated computer actions, making it ideal for tasks that require seamless computer control.

Canonical page: https://skillsregistry.net/skills/ifuryst-open-computer-use  
JSON: https://api.skillsregistry.net/v1/skills/ifuryst-open-computer-use

## Description

Open Computer Use is an open-source computer automation service wrapped as an MCP server. It enables AI agents to control computers using accessibility-based APIs on macOS, Linux, and Windows without requiring proprietary screen capture solutions. The server integrates with multiple AI agents and MCP clients including Codex CLI and Gemini CLI.

## Trust

- **Trust score (0–1):** 0.61
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ifuryst-open-computer-use)
- **Repository:** <https://github.com/ifuryst/open-codex-computer-use>

## 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": "ifuryst-open-computer-use"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ifuryst-open-computer-use` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ifuryst-open-computer-use/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