# mcp-arsr

> Use this tool when you need to refine and verify the accuracy of large language models (LLMs) by leveraging uncertainty-guided retrieval and iterative self-refinement. It solves problems related to claim verification and correction, providing more reliable outputs through a closed-loop system. The tool takes LLM claims as input and outputs verified and corrected information, ideal for applications requiring high accuracy and trustworthiness.

Canonical page: https://skillsregistry.net/skills/jayarrowz-mcp-arsr  
JSON: https://api.skillsregistry.net/v1/skills/jayarrowz-mcp-arsr

## Description

Adaptive Retrieval-Augmented Self-Refinement MCP Server — a closed-loop system that lets LLMs iteratively verify and correct their own claims using uncertainty-guided retrieval.

## Trust

- **Trust score (0–1):** 0.95
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/b2g0yfv5dm)
- **Repository:** <https://github.com/JayArrowz/mcp-arsr>

## 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": "jayarrowz-mcp-arsr"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jayarrowz-mcp-arsr` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jayarrowz-mcp-arsr/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