# mcp-atelier

> mcp-atelier — shunvel-mcp-atelier. Use this tool when you need to build and operate Large Language Model (LLM) agents with enhanced debugging and monitoring capabilities. It solves problems related to model development, deployment, and maintenance by providing live tracing, structured errors, and observability features. With git integration, it accepts code repositories as input and outputs operational LLM agents with improved performance and reliability.

Canonical page: https://skillsregistry.net/skills/shunvel-mcp-atelier  
JSON: https://api.skillsregistry.net/v1/skills/shunvel-mcp-atelier

## Description

MCP workshop for building and operating LLM agents — live tracing, structured errors, and observability built in.

## 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:** 2026-09-28

## Source

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

## 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": "shunvel-mcp-atelier"
    }
  }
}
```

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