# Shell Command

> Use this tool when you need to execute system commands in a controlled environment, allowing AI assistants to interact with the local file system or run specific utilities while maintaining security boundaries. It solves problems related to secure command execution, providing a single tool with built-in security features through an allowlist system. The tool takes shell commands as input and returns results in YAML format with stdout, stderr, and exit code information.

Canonical page: https://skillsregistry.net/skills/egoist-shell-command  
JSON: https://api.skillsregistry.net/v1/skills/egoist-shell-command

## Description

A shell command execution server for the MCP that allows AI assistants to run system commands in a controlled environment. Developed by egoist, this implementation provides a single tool for executing shell commands with built-in security features through an allowlist system. The server uses the ALLOWED_COMMANDS environment variable to explicitly permit specific commands, preventing unauthorized access to potentially dangerous system operations. It returns command results in YAML format with stdout, stderr, and exit code information. This implementation is particularly useful for scenarios where AI assistants need to interact with the local file system or run specific utilities while maintaining security boundaries.

## Trust

- **Trust score (0–1):** 0.94
- **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/egoist-shell-command)
- **Repository:** <https://github.com/egoist/shell-command-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": "egoist-shell-command"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/egoist-shell-command` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/egoist-shell-command/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