# Kryve Agent Evaluation MCP

> Kryve Agent Evaluation MCP — louislaurent1-kryve-agent-eval-mcp. Use this tool when you need to assess and evaluate the performance of AI agents, generating test plans and scoring runs to produce reusable evaluation scorecards. It solves problems related to AI agent testing and validation, providing a standardized framework for evaluation. The tool takes in AI agent runs as input and outputs scored evaluations and reusable scorecards.

Canonical page: https://skillsregistry.net/skills/louislaurent1-kryve-agent-eval-mcp  
JSON: https://api.skillsregistry.net/v1/skills/louislaurent1-kryve-agent-eval-mcp

## Description

Provides read-only tools to generate test plans for AI agents, score agent runs, and produce reusable evaluation scorecards.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/rsojgeqhrh)
- **Repository:** <https://github.com/louislaurent1/kryve-agent-eval-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": "louislaurent1-kryve-agent-eval-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/louislaurent1-kryve-agent-eval-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/louislaurent1-kryve-agent-eval-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