# MCP as a Judge

> Use this tool when you need to validate and ensure the quality of code generated by AI coding assistants, as it evaluates plans, code diffs, and tests to provide safer and higher-quality output. It solves problems related to code reliability and security by enforcing explicit Large Language Model (LLM) evaluations. Ideal for use cases where code accuracy and safety are critical, such as in software development and deployment.

Canonical page: https://skillsregistry.net/skills/othervibes-mcp-as-a-judge  
JSON: https://api.skillsregistry.net/v1/skills/othervibes-mcp-as-a-judge

## Description

A validation layer for AI coding assistants that enforces explicit LLM evaluations on plans, code diffs, and tests to ensure safer and higher-quality code.

## Trust

- **Trust score (0–1):** 0.21
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/z392nucz62)
- **Repository:** <https://github.com/OtherVibes/mcp-as-a-judge>

## 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": "othervibes-mcp-as-a-judge"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/othervibes-mcp-as-a-judge` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/othervibes-mcp-as-a-judge/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