# mcp-eval

> mcp-eval — mohammedibrahim111-mcp-agent-evaluation-harness. Use this tool when you need to evaluate the performance of coding agents in a controlled environment. It solves problems related to inconsistent or biased evaluations by providing structured verification reports with pattern checks and repeat-run comparisons. The tool takes in coding agents and repository tools as inputs and returns detailed evaluation reports as output, making it ideal for use cases requiring deterministic and reliable assessment of coding abilities.

Canonical page: https://skillsregistry.net/skills/mohammedibrahim111-mcp-agent-evaluation-harness  
JSON: https://api.skillsregistry.net/v1/skills/mohammedibrahim111-mcp-agent-evaluation-harness

## Description

Enables deterministic evaluation of coding agents by exposing controlled repository tools and returning structured verification reports with pattern checks and repeat-run comparisons.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/bzfip3x7jm)
- **Repository:** <https://github.com/Mohammedibrahim111/mcp-agent-evaluation-harness>

## 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": "mohammedibrahim111-mcp-agent-evaluation-harness"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mohammedibrahim111-mcp-agent-evaluation-harness` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mohammedibrahim111-mcp-agent-evaluation-harness/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