# mcp-rag-server

> mcp-rag-server — agarwalvishal-mcp-rag-server. Use this tool when you need to create a private knowledge base and enable secure web search for AI clients like Claude, Cursor, and Ollama. It allows you to upload local documents, which remain on your machine, and generates embeddings for private and secure querying. Ideal for use cases requiring data privacy and security, such as sensitive research or enterprise knowledge management.

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

## Description

MCP RAG server — local embeddings, your docs never leave your machine. Private knowledge base + web search for Claude, Cursor, and Ollama. Drop your docs, connect your AI client, done.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/agarwalvishal/mcp-rag-server)

## 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": "agarwalvishal-mcp-rag-server"
    }
  }
}
```

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