# Command Line

> Use this tool when you need to execute common Unix/macOS terminal commands in a controlled and secure environment, solving problems such as file management, system monitoring, and data analysis. It accepts command inputs and returns execution results, with features like command filtering and permission management. Ideal for use cases requiring automation, scripting, or ad-hoc command execution, with support for read, write, and system commands.

Canonical page: https://skillsregistry.net/skills/andresthor-cmd-line  
JSON: https://api.skillsregistry.net/v1/skills/andresthor-cmd-line

## Description

This MCP server allows AI assistants to execute common Unix/macOS terminal commands through a controlled and secure interface. It supports the top ~40 most used terminal commands with appropriate security measures.

Features
- Safe execution of common Unix/macOS commands
- Security validation based on command type
- Command categorization (read, write, system)
- Interactive permission management
- Session-based approval system
- Configuration via environment variables or JSON file
- Comprehensive command filtering and pattern matching
- Support for command chaining via pipes (|), semicolons (;), and ampersands (&)
- Claude Desktop compatibility mode with auto-approval
- Detailed command metadata and help for AI assistants

Read Commands
ls, pwd, cat, less, head, tail, grep, find, which, du, df, file, sort, etc.

Write Commands
cp, mv, rm, mkdir, rmdir, touch, chmod, chown, etc.

System Commands
ps, top, htop, who, netstat, ifconfig, ping, etc.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/andresthor-cmd-line)
- **Repository:** <https://github.com/andresthor/cmd-line-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": "andresthor-cmd-line"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/andresthor-cmd-line` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/andresthor-cmd-line/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