# Shell Access

> Use this tool when you need to execute controlled shell commands for AI clients with a high level of safety and security. It solves problems related to secure shell access and command execution by enforcing an allowlist-driven model and rejecting dangerous operations. The tool takes TOML configuration files as input and outputs the results of approved shell commands, making it ideal for use cases that require restricted and auditable shell access.

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

## Description

Shell Access is a Rust-based MCP server that provides controlled shell execution for AI clients, enforcing an allowlist-driven safety model. Commands are permitted only through explicit TOML configuration files that walk up the directory tree, similar to git. It exposes two tools: one for describing the current allowlist and environment, and one for executing approved shell commands. The server rejects shell metacharacters and maintains a hard denylist of dangerous operations like sudo.

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/devrelopers-shell)
- **Repository:** <https://github.com/devrelopers/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": "devrelopers-shell"
    }
  }
}
```

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