Qurio

v1.0.0Knowledge & Memorystable

Self-hosted RAG engine for AI coding assistants. Ingests technical docs & code repositories locally with structure-aware chunking. Serves grounded context via MCP to prevent hallucinations in software development workflows.

agentic-aiagentic-searchai-agentdocument-ingestiongemini-api
Share:
17
Stars
0
Downloads
0
Weekly
0/5

What is Qurio?

Qurio is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to self-hosted rag engine for ai coding assistants. ingests technical docs & code repositories locally with structure-aware chunking. serves grounded context via mcp to prevent hallucinations in software...

Self-hosted RAG engine for AI coding assistants. Ingests technical docs & code repositories locally with structure-aware chunking. Serves grounded context via MCP to prevent hallucinations in software development workflows.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Self-hosted RAG engine for AI coding assistants. Ingests tec

Use Cases

Self-hosted RAG for code and docs
Structure-aware document chunking
Hallucination prevention in coding
irahardianto

Maintainer

LicenseMIT
Languagego
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx qurio

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Qurio

Qurio is a self-hosted, open-source RAG (Retrieval-Augmented Generation) engine built as a local knowledge base for AI coding assistants. It ingests documentation websites, PDFs, and Markdown files using structure-aware chunking that preserves code blocks and API definitions, then serves relevant context to AI agents via a native MCP endpoint. By running entirely on localhost with Docker Compose, Qurio keeps your private documentation off third-party servers while preventing AI hallucinations — your agent answers questions about your own docs, not generic training data.

Prerequisites

  • Docker and Docker Compose installed and running
  • Google Gemini API key from aistudio.google.com (required for embeddings)
  • An MCP client that supports HTTP transport such as Claude Code, Cursor, Gemini CLI, or Windsurf
  • Optional: Jina AI or Cohere API key for reranking (improves retrieval precision)
1

Clone the repository

Clone the Qurio repository to your local machine.

git clone https://github.com/irahardianto/qurio.git
cd qurio
2

Configure environment variables

Copy the example .env file and add your Google Gemini API key. Gemini is required for generating vector embeddings. Optionally configure a reranking provider for higher precision retrieval.

cp .env.example .env
# Edit .env and set GEMINI_API_KEY=your_key_here
3

Start all services with Docker Compose

Launch the full Qurio stack: Go backend, Vue.js frontend, Python ingestion worker, Weaviate vector store, PostgreSQL, and NSQ queue. Wait about a minute for Weaviate and Postgres to fully initialize.

docker-compose up -d
4

Add data sources via the dashboard

Open the admin dashboard at http://localhost:3000 and click Add Source. Enter a documentation URL for web crawling (e.g., https://docs.docker.com) or upload PDF/Markdown files. Configure crawl depth and exclusion patterns as needed.

5

Configure your MCP client to connect

Add Qurio to your MCP client configuration using the HTTP transport endpoint. Qurio uses a stateless streamable HTTP transport at http://localhost:8081/mcp.

{
  "mcpServers": {
    "qurio": {
      "httpUrl": "http://localhost:8081/mcp"
    }
  }
}

Qurio Examples

Client configuration

Qurio uses HTTP transport (not stdio), so configure your MCP client with an httpUrl pointing to the local server. Ensure Docker Compose is running before connecting.

{
  "mcpServers": {
    "qurio": {
      "httpUrl": "http://localhost:8081/mcp"
    }
  }
}

Prompts to try

After indexing your documentation, ask your AI agent questions that are answered by your specific docs rather than generic training data.

- "How do I configure a healthcheck in Docker Compose?" (after indexing Docker docs)
- "What are the available ingestion options in Qurio?"
- "List all indexed documentation sources"
- "Show me the pages available under the Docker networking documentation"
- "How does our internal API handle authentication?" (after indexing your own API docs)

Troubleshooting Qurio

Docker Compose starts but Weaviate or Postgres fails to be ready

Wait at least 60 seconds after running docker-compose up -d before using the dashboard or MCP endpoint. Run `docker-compose ps` to check service health. If services are unhealthy, run `docker-compose logs weaviate` or `docker-compose logs postgres` to diagnose startup errors.

Embeddings fail or ingestion errors mention Gemini API

Verify your GEMINI_API_KEY in the .env file is valid and has access to the embedding model. Access the Settings page at http://localhost:3000/settings to update the key without restarting the stack. The Gemini API key must have the Generative Language API enabled in Google AI Studio.

MCP client cannot connect to http://localhost:8081/mcp

Confirm the Qurio backend container is running with `docker-compose ps`. The backend Go service exposes the MCP endpoint on port 8081. If you changed ports in .env, update the httpUrl in your MCP client config accordingly. Ensure your client supports native HTTP MCP connections, not just stdio or SSE.

Frequently Asked Questions about Qurio

What is Qurio?

Qurio is a Model Context Protocol (MCP) server that self-hosted rag engine for ai coding assistants. ingests technical docs & code repositories locally with structure-aware chunking. serves grounded context via mcp to prevent hallucinations in software development workflows. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Qurio?

Follow the installation instructions on the Qurio GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Qurio?

Qurio works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Qurio free to use?

Yes, Qurio is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "qurio": { "command": "npx", "args": ["-y", "qurio"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Qurio?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides