# mcp-eval-harness

> Use this tool when you need to evaluate the quality and accuracy of code generated by large language models (LLMs) or other coding systems, leveraging sandboxed execution and MCP-based scoring to assess performance and reliability. It solves problems related to code validation, debugging, and optimization, providing a secure and controlled environment for testing. The tool accepts code inputs and returns quality scores and execution results as outputs.

Canonical page: https://skillsregistry.net/skills/salmankhan-prs-mcp-eval-harness  
JSON: https://api.skillsregistry.net/v1/skills/salmankhan-prs-mcp-eval-harness

## Description

MCP-based code evaluation harness — sandboxed execution + LLM quality scoring.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/a86wo2m3du)
- **Repository:** <https://github.com/salmankhan-prs/mcp-eval-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": "salmankhan-prs-mcp-eval-harness"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/salmankhan-prs-mcp-eval-harness` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/salmankhan-prs-mcp-eval-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