# shell-mcp

> Use this tool when you need to execute shell commands securely, with features like command whitelisting and directory restrictions. It solves problems related to unauthorized command execution and data breaches by providing multiple security layers. Ideal for use cases requiring secure shell command execution, such as automated tasks or restricted user environments.

Canonical page: https://skillsregistry.net/skills/kg912-shell-mcp  
JSON: https://api.skillsregistry.net/v1/skills/kg912-shell-mcp

## Description

Enables secure execution of shell commands via MCP with multiple security layers including command whitelisting and directory restrictions.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/j021wx3szm)
- **Repository:** <https://github.com/kg912/shell-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": "kg912-shell-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kg912-shell-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kg912-shell-mcp/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