# minirag

> minirag — mck-s-minirag-pgvector-mcp. Use this tool when you need to enable AI agents to search and retrieve answers from locally stored documents, providing a self-hosted solution with local embeddings and no API key requirement. It solves the problem of securely and efficiently retrieving grounded answers from ingested documents, ideal for use cases where data privacy and autonomy are crucial. The minirag tool takes in locally ingested documents and outputs relevant answers via MCP tools, making it a suitable solution for applications requiring local knowledge retrieval.

Canonical page: https://skillsregistry.net/skills/mck-s-minirag-pgvector-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mck-s-minirag-pgvector-mcp

## Description

MCP server for a self-hosted RAG system that enables AI tools to search and retrieve grounded answers from locally ingested documents via MCP tools, with local embeddings and no API key required.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ly0jrfqykj)
- **Repository:** <https://github.com/mck-s/minirag-pgvector-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": "mck-s-minirag-pgvector-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mck-s-minirag-pgvector-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mck-s-minirag-pgvector-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