# RAG MCP Server

> Use this tool when you need to enhance your knowledge base with advanced search and reranking capabilities, supporting multimodal embeddings and multiple knowledge sources. It solves problems of inefficient information retrieval and ranking, particularly in applications with diverse data types and sources. The RAG MCP Server takes in queries and knowledge base inputs, outputting relevant and accurately ranked results, ideal for use cases requiring robust and flexible information retrieval systems.

Canonical page: https://skillsregistry.net/skills/sglwsjxh-rag-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sglwsjxh-rag-mcp

## Description

A RAG knowledge base MCP server that adds vector search and reranking capabilities to opencode, supporting multimodal embeddings, multiple knowledge bases, and local storage.

## Trust

- **Trust score (0–1):** 0.93
- **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/b79yv8w7va)
- **Repository:** <https://github.com/sglwsjxh/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": "sglwsjxh-rag-mcp"
    }
  }
}
```

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