git clone https://github.com/Rubrum95/rag-mcp-server
cd rag-mcp-server
pip install .

pip install ".[ocr]"

# macOS
brew install tesseract

# Windows — download installer from:
# https://github.com/UB-Mannheim/tesseract/wiki

# Linux
sudo apt install tesseract-ocr tesseract-ocr-spa

{
  "mcpServers": {
    "rag": {
      "command": "rag-mcp-server"
    }
  }
}

Ask Claude: "Index ~/projects/my-research"
→ Calls rag_index, processes all PDFs and code files

Ask Claude: "What does the paper say about ocean warming?"
→ Calls rag_query, returns exact text with page citations

Ask Claude: "Update the my-research index"
→ Calls rag_update, only processes new/changed files

Ask Claude: "List my indexed projects"
→ Shows all projects with file/chunk counts

Your files → Text extraction → Chunking → Embeddings → ChromaDB
                (+ OCR if needed)

Your question → Embedding → Cosine similarity search → Top chunks
                                                          ↓
                                            Claude reads exact text
                                            and responds with citations