README - pdf-rag-mcp-server by hyson666

PDF RAG MCP Server

A powerful document knowledge base system that leverages PDF processing, vector storage, and MCP (Model Context Protocol) to provide semantic search capabilities for PDF documents. This system allows you to upload, process, and query PDF documents through a modern web interface or via the MCP protocol for integration with AI tools like Cursor.

Features

PDF Document Upload & Processing: Upload PDFs and automatically extract, chunk, and vectorize content
Real-time Processing Status: WebSocket-based real-time status updates during document processing
Semantic Search: Vector-based semantic search across all processed documents
MCP Protocol Support: Integrate with AI tools like Cursor using the Model Context Protocol
Modern Web Interface: React/Chakra UI frontend for document management and querying
Fast Dependency Management: Uses uv for efficient Python dependency management

System Architecture

The system consists of:

FastAPI Backend: Handles API requests, PDF processing, and vector storage
React Frontend: Provides a user-friendly interface for managing documents
Vector Database: Stores embeddings for semantic search
WebSocket Server: Provides real-time updates on document processing
MCP Server: Exposes knowledge base to MCP-compatible clients

Quick Start

Prerequisites

Python 3.8 or later
uv - Fast Python package installer and resolver
Git
Cursor (optional, for MCP integration)

Quick Installation and Startup with uv and run.py

Clone the repository:

git clone https://github.com/yourusername/PdfRagMcpServer.git
cd PdfRagMcpServer

Install uv if you don't have it already:

curl -sS https://astral.sh/uv/install.sh | bash

Install dependencies using uv:

uv init .
uv venv
source .venv/bin/activate
uv pip install -r backend/requirements.txt

Start the application with the convenient script:
```
uv run run.py
```
Access the web interface at http://localhost:8000
Using with Cursor

Go Settings -> Cursor Settings -> MCP -> Add new global MCP server, paste below into your Cursor ~/.cursor/mcp.json file. See Cursor MCP docs for more info.

{
  "mcpServers": {
    "pdf-rag": {
      "url": "http://localhost:7800/mcp"
    }
  }
}

You could also change localhost into the host ip you deployed the service. After this confige added to the mcp json, you will see the mcp server showes at the Cursor mcp config page, switch it on to enable the server:

Building the Frontend (For Developers)

If you need to rebuild the frontend, you have two options:

Option 1: Using the provided script (recommended)

# Make the script executable if needed
chmod +x build_frontend.py

# Run the script
./build_frontend.py

This script will automatically:

Install frontend dependencies
Build the frontend
Copy the build output to the backend's static directory

Option 2: Manual build process

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

# Build the frontend
npm run build

# Create static directory if it doesn't exist
mkdir -p ../backend/static

# Copy build files
cp -r dist/* ../backend/static/

After building the frontend, you can start the application using the run.py script.

Simple Production Setup

For a production environment where the static files have already been built:

Place your pre-built frontend in the backend/static directory

Start the server:

cd backend
uv pip install -r requirements.txt
python -m app.main

Development Setup (Separate Services)

If you want to run the services separately for development:

Backend

Navigate to the backend directory:
```
cd backend
```
Install the dependencies with uv:
```
uv pip install -r requirements.txt
```

Run the backend server:

python -m uvicorn app.main:app --host 0.0.0.0 --port 8000 --reload

Frontend

Navigate to the frontend directory:
```
cd frontend
```
Install the dependencies:
```
npm install
```
Run the development server:
```
npm run dev
```

Usage

Uploading Documents

Access the web interface at http://localhost:8000
Click on "Upload New PDF" and select a PDF file
The system will process the file, showing progress in real-time
Once processed, the document will be available for searching

Searching Documents

Use the search functionality in the web interface
Or integrate with Cursor using the MCP protocol

MCP Integration with Cursor

Open Cursor
Go to Settings → AI & MCP
Add Custom MCP Server with URL: http://localhost:8000/mcp/v1
Save the settings
Now you can query your PDF knowledge base directly from Cursor

Troubleshooting

Connection Issues

Verify that port 8000 is not in use by other applications
Check that the WebSocket connection is working properly
Ensure your browser supports WebSockets

Processing Issues

Check if your PDF contains extractable text (some scanned PDFs may not)
Ensure the system has sufficient resources (memory and CPU)
Check the backend logs for detailed error messages

Project Structure

PdfRagMcpServer/
├── backend/               # FastAPI backend
│   ├── app/
│   │   ├── __init__.py
│   │   ├── main.py        # Main FastAPI application
│   │   ├── database.py    # Database models
│   │   ├── pdf_processor.py # PDF processing logic
│   │   ├── vector_store.py # Vector database interface
│   │   └── websocket.py   # WebSocket handling
│   ├── static/            # Static files for the web interface
│   └── requirements.txt   # Backend dependencies
├── frontend/              # React frontend
│   ├── public/
│   ├── src/
│   │   ├── components/    # UI components
│   │   ├── context/       # React context
│   │   ├── pages/         # Page components
│   │   └── App.jsx        # Main application component
│   ├── package.json       # Frontend dependencies
│   └── vite.config.js     # Vite configuration
├── uploads/               # PDF file storage
└── README.md              # This documentation

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.