# CLI

> Use this tool when you need to securely execute shell commands for AI models, enabling interactions with the file system, utilities, and scripts in a controlled environment. It solves problems in system administration, development workflows, and AI assistant development, providing a secure bridge between AI systems and local shell commands. The CLI server takes shell commands as input and returns execution results, making it ideal for use cases requiring command-line tool integration while maintaining security.

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

## Description

This MCP server, developed by hdresearch, provides secure shell command execution capabilities for AI models. Built in Node.js, it integrates with Claude Desktop and enables AI assistants to run shell commands in a controlled environment. The implementation stands out through its focus on security, using command blacklisting, existence validation, and comprehensive error handling. By bridging AI models with the local shell, this server allows AI systems to interact with the file system, run utilities, and execute scripts. It is particularly useful for scenarios like system administration, development workflows, and building AI assistants that can leverage command-line tools while maintaining a strong security posture.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **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/hdresearch-shell)
- **Repository:** <https://github.com/hdresearch/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": "hdresearch-shell"
    }
  }
}
```

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