# self_rag_mcp

> self_rag_mcp — firewizard-v9-self-rag-mcp. Use this tool when you need to generate accurate and relevant text based on retrieved information, and want to leverage self-reflective retrieval and verification capabilities to ensure answer grounding and document relevance. It solves problems of information retrieval and text generation by providing a robust interface for retrieving and grading relevant documents, and verifying answer accuracy. This tool is ideal for use cases requiring reliable and informed text generation, with inputs of natural language prompts and outputs of generated text and verified answers.

Canonical page: https://skillsregistry.net/skills/firewizard-v9-self-rag-mcp  
JSON: https://api.skillsregistry.net/v1/skills/firewizard-v9-self-rag-mcp

## Description

Enables self-reflective retrieval-augmented generation with LLM-driven retrieval decisions, document relevance grading, answer grounding verification, and automatic retries, exposed through MCP tools over SSE.

## 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:** ai-ml
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/pfq0ifn5cp)
- **Repository:** <https://github.com/FireWizard-V9/self_rag_mcp>

## 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": "firewizard-v9-self-rag-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/firewizard-v9-self-rag-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/firewizard-v9-self-rag-mcp/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