# mcp-reap

> mcp-reap — caarlosgg-mcp-reap. Use this tool when you need to detect and clean up orphaned processes from AI tools like Claude Code, Cursor, Codex, and Aider, to free up system resources and prevent potential errors. It takes no input and outputs a cleaned system environment, working seamlessly on Windows, macOS, and Linux operating systems. Ideal for use when experiencing system slowdowns or errors after using AI tools, with integration capabilities via git.

Canonical page: https://skillsregistry.net/skills/caarlosgg-mcp-reap  
JSON: https://api.skillsregistry.net/v1/skills/caarlosgg-mcp-reap

## Description

Detecta y limpia procesos huérfanos de herramientas de IA (Claude Code, Cursor, Codex, Aider). Funciona en Windows, macOS y Linux.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-23

## Source

- **Source listing:** [GitHub](https://github.com/Caarlosgg/mcp-reap)

## 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": "caarlosgg-mcp-reap"
    }
  }
}
```

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