# mcp-shell

> Use this tool when you need to securely execute commands over HTTP with token-based authentication, to solve problems related to remote command execution and security. It provides a default-deny allowlist and rejects shell metacharacters, ensuring a secure interface for executing authorized commands. Ideal for use cases requiring secure, controlled command execution in remote or restricted environments.

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

## Description

Provides a secure, token-authenticated command execution tool over MCP Streamable HTTP, with a default-deny allowlist and shell metacharacter rejection.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/m1w39x2okz)
- **Repository:** <https://github.com/imajeure/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": "imajeure-mcp-shell"
    }
  }
}
```

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