How do I use MCP-RAG?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP-RAG what does my employee handbook say about vacation days?" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

MCP-RAG

Your Personal NotebookLM for Claude Desktop

Universal RAG (Retrieval-Augmented Generation) MCP server for Claude Desktop. Index documents via CLI, search them in Claude Desktop with 0% hallucination.

License: MIT Node.js Version Python Version

What is MCP-RAG?

Think of it as NotebookLM for Claude Desktop:

📚 Index any documents: PDF, Word, PowerPoint, Excel, 한글, TXT, MD
🔍 Natural language search: Ask questions in Claude Desktop
✅ 0% Hallucination: Answers based ONLY on your documents
💻 100% Local: All data stays on your computer (ChromaDB)
🎯 Simple workflow: CLI for indexing → Claude Desktop for searching

Architecture

┌─────────────────────┐
│  Your Documents     │
│  (PDF, DOCX, etc)   │
└──────────┬──────────┘
           │
           ▼
    [CLI: npm run cli add]
           │
           ▼
┌─────────────────────┐
│   ChromaDB Server   │ ◄─── Vector embeddings
│   (localhost:8000)  │
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│   MCP-RAG Server    │
└──────────┬──────────┘
           │
           ▼
┌─────────────────────┐
│  Claude Desktop     │ ◄─── You ask questions here!
└─────────────────────┘

Two-Part System:

CLI = Document management (add, delete, list)
Claude Desktop = Search and Q&A

Quick Start

1. Install

git clone https://github.com/seanshin0214/mcp-rag.git
cd mcp-rag
npm install
pip install chromadb

2. Start ChromaDB Server

Keep this running in a separate terminal:

chroma run --host localhost --port 8000

3. Add Documents (CLI)

# Add single document
npm run cli add school "path/to/regulations.pdf"

# Add multiple documents
npm run cli add research "paper1.pdf"
npm run cli add research "paper2.docx"
npm run cli add work "handbook.pptx"

Supported formats:

Documents: PDF, DOCX, HWP, TXT, MD
Presentations: PPTX
Spreadsheets: XLSX, XLS

4. Configure Claude Desktop

Windows: %APPDATA%\Claude\claude_desktop_config.json

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

✨ Option 1: Auto-start ChromaDB (Recommended)

{
  "mcpServers": {
    "mcp-rag": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-rag/start-with-chroma.js"]
    }
  }
}

This automatically starts ChromaDB before starting MCP-RAG!

Option 2: Manual ChromaDB start

{
  "mcpServers": {
    "mcp-rag": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-rag/src/index.js"]
    }
  }
}

You need to manually run chroma run --host localhost --port 8000 before starting.

Important: Use your actual installation path!

5. Restart Claude Desktop

6. Ask Questions!

In Claude Desktop:

"What does the school collection say about attendance?"

"Search the research collection for methodology"

"Show me all my collections"

CLI Commands

# Add document
npm run cli add <collection> <file> [-d "description"]

# List all collections
npm run cli list

# Get collection info
npm run cli info <collection>

# Search test
npm run cli search <collection> "query"

# Delete collection
npm run cli delete <collection>

Examples

# Add with description
npm run cli add school "regulations.pdf" -d "School regulations 2024"

# Add multiple files (PowerShell)
Get-ChildItem "*.docx" | ForEach-Object {
    npm run cli add MyCollection $_.FullName
}

# Check what's indexed
npm run cli list
npm run cli info school

MCP Tools (Claude Desktop)

When you ask questions in Claude Desktop, these tools are automatically used:

Tool	Description
`search_documents`	Search in specific collection or all collections
`list_collections`	List all available collections
`get_collection_info`	Get details about a collection

Note: Document addition is CLI-only, not available in Claude Desktop.

How It Works

Indexing (CLI)

1. Read file (PDF/DOCX/PPTX/etc)
2. Extract text
3. Split into 500-token chunks (50-token overlap)
4. Generate embeddings (ChromaDB)
5. Store in collection

Searching (Claude Desktop)

1. You ask: "What's the attendance policy?"
2. MCP-RAG searches ChromaDB
3. Returns top 5 most relevant chunks
4. Claude answers using ONLY those chunks

Use Cases

📚 Students

npm run cli add math "calculus-textbook.pdf"
npm run cli add physics "lecture-notes.docx"

→ "Explain the concept of derivatives from my math collection"

🏢 Professionals

npm run cli add company "employee-handbook.pdf"
npm run cli add project "requirements.docx"

→ "What's our vacation policy?"

🔬 Researchers

npm run cli add literature "papers/*.pdf"
npm run cli add notes "research-notes.md"

→ "Summarize the methodology from the literature collection"

Features

✅ Multi-collection support - Organize by topic
✅ Semantic search - ChromaDB vector embeddings
✅ Source attribution - See which document/chunk
✅ Relevance scoring - Know how confident the match is
✅ Multiple file formats - PDF, DOCX, PPTX, XLSX, HWP, TXT, MD
✅ 100% local - No cloud, all on your machine
✅ 0% hallucination - Only document-based answers

Comparison

Feature	NotebookLM	MCP-RAG
Platform	Google Cloud	Local
AI Model	Gemini	Claude
Privacy	Cloud	100% Local
Multi-collection	❌	✅
CLI	❌	✅
Cost	Free (limited)	Free (unlimited)

Troubleshooting

ChromaDB Connection Error

Problem: Cannot connect to ChromaDB

Solution:

chroma run --host localhost --port 8000

Keep this terminal open!

Claude Desktop: MCP Server Not Showing

Check claude_desktop_config.json syntax
Use absolute path (not relative)
Restart Claude Desktop completely
Check ChromaDB is running

No Search Results

# Verify documents are indexed
npm run cli list
npm run cli info <collection>

# Re-index if needed
npm run cli add <collection> <file>

Advanced

Batch Add Files

PowerShell:

Get-ChildItem "C:\docs\*.pdf" | ForEach-Object {
    npm run cli add MyCollection $_.FullName
}

Bash:

for f in /path/to/docs/*.pdf; do
    npm run cli add MyCollection "$f"
done

Custom Chunk Size

Edit src/indexer.js:

const CHUNK_SIZE = 500;      // Tokens per chunk
const CHUNK_OVERLAP = 50;    // Overlap between chunks

Larger chunks = more context, fewer chunks Smaller chunks = more precise, more chunks

Project Structure

mcp-rag/
├── src/
│   ├── index.js       # MCP server
│   ├── cli.js         # CLI tool
│   └── indexer.js     # Document processing
├── chroma/            # ChromaDB data (auto-created)
├── package.json
├── README.md
├── QUICK_START.md
└── HOW_TO_USE.md

Requirements

Node.js 18+
Python 3.8+ (for ChromaDB)
Claude Desktop (latest version)

Contributing

Contributions welcome! This is a universal tool that can benefit many users.

License

MIT License - see LICENSE

Credits

Built with:

Model Context Protocol (MCP) - Anthropic
ChromaDB - Vector database
pdf-parse - PDF extraction
mammoth - DOCX extraction
officeparser - PPTX extraction
xlsx - Excel extraction
node-hwp - 한글 extraction

MCP-RAG - Your documents, Claude's intelligence, zero hallucination.

MCP-RAG

MCP-RAG

What is MCP-RAG?

Architecture

Quick Start

1. Install

2. Start ChromaDB Server

3. Add Documents (CLI)

4. Configure Claude Desktop

5. Restart Claude Desktop

6. Ask Questions!

CLI Commands

Examples

MCP Tools (Claude Desktop)

How It Works

Indexing (CLI)

Searching (Claude Desktop)

Use Cases

📚 Students

🏢 Professionals

🔬 Researchers

Features

Comparison

Troubleshooting

ChromaDB Connection Error

Claude Desktop: MCP Server Not Showing

No Search Results

Advanced

Batch Add Files

Custom Chunk Size

Project Structure

Requirements

Contributing

License

Credits

Resources

Appeared in Searches

Latest Blog Posts

MCP directory API