# MCP Experiments

> Use this tool when you need to execute system commands on macOS from large language models (LLMs) while ensuring safety and control. It solves problems related to automating tasks, interacting with the operating system, and testing scripts, by providing a secure interface for running Bash and AppleScript commands. The tool accepts LLM inputs and outputs command results, making it ideal for use cases requiring automated system interactions on macOS.

Canonical page: https://skillsregistry.net/skills/jordanperr-mcp-experiments  
JSON: https://api.skillsregistry.net/v1/skills/jordanperr-mcp-experiments

## Description

Provides tools for executing Bash and AppleScript commands from LLMs on macOS, with safety modes.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-01

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/oirjflndxn)
- **Repository:** <https://github.com/jordanperr/mcp-experiments>

## 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": "jordanperr-mcp-experiments"
    }
  }
}
```

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