# Shell Command Executor

> Use this tool when you need to execute shell commands securely, with controlled access and comprehensive security features, to solve problems such as automating system tasks or integrating with external systems while maintaining security boundaries. It takes in shell commands as input and returns structured JSON output with execution metadata, making it ideal for use cases requiring secure terminal operations. It is particularly useful in scenarios where AI assistants need to run controlled terminal commands with limited access.

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

## Description

MCP-Shell provides a secure interface for executing shell commands through the Model Context Protocol, allowing AI assistants to run controlled terminal operations. Built in Go, it implements comprehensive security features including allowlists for commands, pattern-based blocking, execution timeouts, and output size limits defined in a YAML configuration. The server exposes a single tool that executes commands and returns structured JSON with stdout, stderr, exit codes, and execution metadata, making it ideal for scenarios requiring controlled system access while maintaining security boundaries.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/sonirico-shell)
- **Repository:** <https://github.com/sonirico/mcp-shell>

## 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": "sonirico-shell"
    }
  }
}
```

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