Qurio
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.
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
Maintainer
Works with
Installation
Manual Installation
npx qurioConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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)
Clone the repository
Clone the Qurio repository to your local machine.
git clone https://github.com/irahardianto/qurio.git
cd qurioConfigure 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_hereStart 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 -dAdd 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.
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.
Qurio Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Qurio? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
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.
Set Up Qurio in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.