# Verity

> Verity — johnnyryan-verity. Use this tool when you need to verify the accuracy of large language model (LLM) claims and minimize false information. Verity checks LLM outputs to identify potential errors, providing a reliable interface for inputting claims and outputting verified results. Ideal for applications where trustworthiness of LLM-generated content is crucial, such as research, content creation, or decision-making processes.

Canonical page: https://skillsregistry.net/skills/johnnyryan-verity  
JSON: https://api.skillsregistry.net/v1/skills/johnnyryan-verity

## Description

MCP to check and minimise false LLM claims

## Trust

- **Trust score (0–1):** 0.76
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/johnnyryan/Verity)

## 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": "johnnyryan-verity"
    }
  }
}
```

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