# OpenRAG MCP Server

> Use this tool when you need to generate and manage knowledge graphs over personal documents while maintaining data privacy. It solves problems related to information retrieval and document analysis by providing three parallel RAG strategies: Traditional, Contextual, and Graph RAG. The OpenRAG MCP Server takes in personal documents as input and outputs a locally stored knowledge graph, ideal for use cases where data privacy is a top priority.

Canonical page: https://skillsregistry.net/skills/janik96v-openrag  
JSON: https://api.skillsregistry.net/v1/skills/janik96v-openrag

## Description

An open-source MCP server for RAG over personal documents. Supports three parallel strategies — Traditional, Contextual, and Graph RAG — with all data stored locally for privacy.

## Trust

- **Trust score (0–1):** 0.31
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/vevqnbbgnw)
- **Repository:** <https://github.com/janik96v/OpenRAG>

## 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": "janik96v-openrag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/janik96v-openrag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/janik96v-openrag/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