---
title: Invoice RAG with MCP
emoji: 📄
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 5.33.1
app_file: app.py
tags:
  - Agents-MCP-Hackathon
  - mcp-server-track
pinned: false
license: mit
---

# 📄 Invoice RAG System with MCP Integration

An intelligent system for processing and querying invoice data using RAG (Retrieval Augmented Generation) with MCP (Model Context Protocol) support.

## DEMO
[DemoVideo](https://drive.google.com/file/d/1R6LG7qwtsaHLWZMv02NeJK_cqXaa8e-n/view?usp=sharing)

## 🚀 Features

- **PDF Invoice Processing**: Extract and analyze invoice data
- **RAG System**: Intelligent document retrieval and question answering  
- **Multiple LLM Support**: Groq integration with various models
- **MCP Integration**: Expose tools via Model Context Protocol
- **Interactive UI**: Clean Gradio interface

## 🔧 Setup

1. **Set API Keys**: Add your `GROQ_API_KEY` in the Space settings
2. **Upload Invoices**: Use the training tab to process your PDFs
3. **Query Data**: Ask questions about your invoices
4. **MCP Tools**: Access structured data extraction tools

## 📝 Usage

1. **Train**: Upload invoice PDFs to train the RAG system
2. **Query**: Ask natural language questions about your invoices
3. **Extract**: Use MCP tools for structured data extraction

## 🔑 Required Environment Variables

- `GROQ_API_KEY`: Your Groq API key for LLM access

## 🛠️ MCP Integration

The system exposes these MCP tools:
- `query_invoice_info`: Extract information from invoices
- `get_invoice_summary`: Get summary of processed invoices  
- `extract_specific_field`: Extract specific fields
- `list_available_invoices`: List available invoice sources