RAG_MCP
A RAG-ready MCP server for semantic PDF search with OCR, FAISS, and transformers—plug into any MCP client and retrieve intelligent answers within your MCP client.
what is RAG_MCP?
RAG_MCP is a RAG-ready MCP server designed for semantic PDF search, utilizing OCR, FAISS, and transformers to provide intelligent answers.
how to use RAG_MCP?
To use RAG_MCP, integrate it with any MCP client, allowing you to perform semantic searches on PDF documents and retrieve relevant information.
key features of RAG_MCP?
- Semantic PDF search capabilities
- Integration with OCR for text recognition
- Utilization of FAISS for efficient similarity search
- Transformer models for intelligent answer retrieval
use cases of RAG_MCP?
- Searching academic papers for specific information.
- Retrieving data from scanned documents.
- Enhancing document management systems with intelligent search features.
FAQ from RAG_MCP?
- What is the primary function of RAG_MCP?
RAG_MCP is designed to perform semantic searches on PDF documents, providing intelligent answers based on the content.
- Is RAG_MCP easy to integrate?
Yes! RAG_MCP can be easily plugged into any MCP client for seamless functionality.
- What technologies does RAG_MCP use?
RAG_MCP utilizes OCR, FAISS, and transformer models to enhance its search capabilities.
RAG_MCP
A RAG-ready MCP server for semantic PDF search with OCR, FAISS, and transformers—plug into any MCP client and retrieve intelligent answers within your MCP client.
Step 1: Create virtual env and install requirements
curl -LsSf https://astral.sh/uv/install.sh | sh
uv init rag_mcp
cd rag_mcp
uv venv
source .venv/bin/activate
uv pip install -r requirements.txt
brew install tesseract
Step 2a: Add config to the Claude MCP client
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
...
{
"mcpServers": {
"rag": {
"command": "/Users/XXX/.local/bin/uv",
"args": [
"--directory",
"/Users/XXX/Documents/RAG_MCP",
"run",
"rag.py"
]
}
}
}
Step 2b: Add config to the Cursor MCP client
code ~/.cursor/mcp.json
...
{
"mcpServers": {
"rag": {
"command": "/Users/XXX/Documents/RAG_MCP/start.sh",
"args": []
}
}
}
Step 5: Make MCP server executable
chmod +x start.sh
chmod +x rag.py
Step 6: Run MCP server (Claude Desktop)
uv run rag.py
Step 7: Run MCP client and query
Parse the pdfs and tell me about 18 Church St. and what significance it has.
