# agent-eval-mcp

> Use this tool when you need to evaluate AI agent outputs and ensure quality gates in continuous integration pipelines. It provides a stdio server for regression comparisons and canary promotion decisions, enabling data-driven decisions on agent performance. The agent-eval-mcp tool accepts AI agent outputs as input and returns evaluation results, facilitating informed decisions on agent quality and reliability.

Canonical page: https://skillsregistry.net/skills/ad-github1-enterprise-ai-agent-evaluation-platform  
JSON: https://api.skillsregistry.net/v1/skills/ad-github1-enterprise-ai-agent-evaluation-platform

## Description

An MCP-style stdio server for evaluating AI agent outputs, enabling CI-friendly quality gates, regression comparisons, and canary promotion decisions.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/cq66sj7g4r)
- **Repository:** <https://github.com/ad-github1/ENTERPRISE-AI-AGENT-EVALUATION-PLATFORM>

## 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": "ad-github1-enterprise-ai-agent-evaluation-platform"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ad-github1-enterprise-ai-agent-evaluation-platform` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ad-github1-enterprise-ai-agent-evaluation-platform/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