# computer-use

> computer-use — taotao135791-bit-oc-computer-use. Use this tool when you need to automate interactions with a macOS desktop, capture screenshots, or simulate user input like clicks and keystrokes. It solves problems like automated testing, desktop automation, and remote control by providing a JSON-RPC runtime with 7 MCP tools. It takes in JSON-RPC requests and outputs image content blocks, making it ideal for use cases where external agents need to drive a desktop environment securely.

Canonical page: https://skillsregistry.net/skills/taotao135791-bit-oc-computer-use  
JSON: https://api.skillsregistry.net/v1/skills/taotao135791-bit-oc-computer-use

## Description

Provides a JSON-RPC computer use runtime for macOS, exposing 7 MCP tools (observe/act/inspect/session/cancel/trace) as image content blocks so external agents like Claude Code, Pi, OpenCode, or Codex CLI can capture screenshots and drive the desktop with clicks, keys, and typing while enforcing session locking, stale-frame protection, and trace redaction server-side.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/f142835p6k)
- **Repository:** <https://github.com/taotao135791-bit/oc-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": "taotao135791-bit-oc-computer-use"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/taotao135791-bit-oc-computer-use` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/taotao135791-bit-oc-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