# sh.antrieb/antrieb

> Use this tool when you need to validate and refine AI-generated infrastructure code, as it runs the code on real VMs and self-corrects until it works, solving issues with code reliability and stability. It takes AI-generated infra code as input and outputs validated, functional code. Ideal for use cases where automated code testing and correction are crucial, such as in DevOps and cloud infrastructure development.

Canonical page: https://skillsregistry.net/skills/sh-antrieb-antrieb  
JSON: https://api.skillsregistry.net/v1/skills/sh-antrieb-antrieb

## Description

Validates AI infra code on real VMs. Self-corrects until it works. No containers, no sandboxes.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/sh.antrieb%2Fantrieb)
- **Repository:** <https://github.com/jade-pico/antrieb-mcp-server>

## Use it

MCP endpoint published by the skill: `https://antrieb.sh/mcp`

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": "sh-antrieb-antrieb"
    }
  }
}
```

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