RAGFlow + MCP: Turning Your Best RAG Config Into a Production Assistant

A developer describes how to turn optimal RAG configurations into a production-ready assistant using RAGFlow, an open-source tool with 80,000+ GitHub stars. RAGFlow's DeepDoc engine preserves document structure, supports multiple formats, and can be deployed as an MCP server for integration with tools like Claude and Cursor. The assistant provides source-cited answers and runs self-hosted for privacy compliance.

You've found your best RAG settings. Now how do you turn them into a real assistant your team uses every day? In my previous post I covered how tools like AutoRAG and RAGBuilder can measure and find the best RAG combination embedding, chunk size, reranker... for your data. But those tools are measuring instruments — they tell you "this is the best config" and stop there. They are not the assistant that users talk to, upload documents to, and ask questions. For building that assistant, the most mature open-source tool I can recommend: RAGFlow https://github.com/infiniflow/ragflow 80,000+ GitHub stars . Most RAG tools read a PDF as flat text. RAGFlow's DeepDoc engine treats the document like a human would: it preserves table structure, applies OCR to scanned pages, and understands heading hierarchy. Word, Excel, PowerPoint, scanned copies, images, web pages — it handles them all. Create a separate knowledge base per department or client → upload documents → pick your embedding model and chunking template this is where you plug in the winning settings from your measurement tools → RAGFlow parses and indexes → your chat assistant is ready. Answers come with citations — users see exactly which part of which document the answer came from, cutting hallucination risk. RAGFlow can run as an MCP Model Context Protocol server. That means you can plug your document assistant directly into MCP-enabled tools like Claude and Cursor. Your teammate sits in Claude and asks, "what was the penalty clause in last year's supplier contract?" — Claude searches your RAGFlow knowledge base over MCP and returns a source-cited answer from your own documents. No new interface to learn; the assistant lives inside the tools your team already uses. Documents → RAGFlow OCR + parse + chunk + index → Knowledge bases per department/client → Chat UI + API + MCP → Web, Slack, or clients like Claude Everything runs self-hosted — your data never leaves your own servers. A critical advantage for privacy and compliance GDPR/KVKK . A document assistant built on measurement instead of guesswork, with citations, running on your own servers — fully possible today with open-source tools alone.