# groundcheck

> groundcheck — offquestxo-groundcheck. Use this tool when you need to evaluate the accuracy and reliability of Retrieval-Augmented Generation (RAG) model outputs. Groundcheck provides faithfulness scoring, hallucination detection, and retrieval quality metrics, helping to identify potential issues and improve overall model performance. It offers a straightforward interface with zero API keys required, using MCP sampling for efficient evaluation.

Canonical page: https://skillsregistry.net/skills/offquestxo-groundcheck  
JSON: https://api.skillsregistry.net/v1/skills/offquestxo-groundcheck

## Description

An MCP server that lets any AI agent evaluate RAG outputs -- faithfulness scoring, hallucination detection, and retrieval quality metrics -- with zero API keys, using MCP sampling.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/kpfukzvt5g)
- **Repository:** <https://github.com/offquestxo/groundcheck>

## 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": "offquestxo-groundcheck"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/offquestxo-groundcheck` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/offquestxo-groundcheck/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