# decisions-judge-mcp

> decisions-judge-mcp — clouatre-labs-decisions-judge-mcp. Use this tool when you need to evaluate coding decisions with a large language model (LLM) judge, providing typed decisions such as yes/no probabilities, choices, and scores. It solves problems related to coding agent decision-making, offering a server-based solution with git capabilities. The tool takes in coding-related inputs and outputs probabilistic judgments, making it ideal for use cases requiring informed decision-making in coding contexts.

Canonical page: https://skillsregistry.net/skills/clouatre-labs-decisions-judge-mcp  
JSON: https://api.skillsregistry.net/v1/skills/clouatre-labs-decisions-judge-mcp

## Description

Typed decisions for AI agents as an MCP tool: yes/no probability (noul), choice, and score in one fast request. Backed by the TypeSafe System One model.

## 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:** Apache-2.0
- **Updated:** 2026-09-26

## Source

- **Source listing:** [GitHub](https://github.com/clouatre-labs/decisions-judge-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": "clouatre-labs-decisions-judge-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/clouatre-labs-decisions-judge-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/clouatre-labs-decisions-judge-mcp/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