# 🔍 Company Research Agent with MCP + OpenAI + Gradio

An intelligent company research and competitive analysis tool that combines the power of **Model Context Protocol (MCP)**, **OpenAI GPT-4**, and **Gradio** to deliver comprehensive business intelligence.

## 🌟 Features

- **Automated Company Research**: Search for company information using MCP tools
- **Competitor Analysis**: Automatically identify and analyze competitors
- **Business Model Analysis**: Understand company operations and revenue streams
- **Market Keywords Extraction**: Extract relevant keywords describing the competitive landscape
- **AI-Powered Insights**: OpenAI synthesizes research into actionable executive summaries
- **Interactive UI**: Beautiful Gradio interface for easy interaction

## 🏗️ Architecture

```
┌─────────────────┐
│  Gradio UI      │
│  (Frontend)     │
└────────┬────────┘
         │
         ▼
┌─────────────────┐      ┌──────────────────┐
│  OpenAI GPT-4   │◄────►│  MCP Server      │
│  (AI Analysis)  │      │  (Research Tools)│
└─────────────────┘      └──────────────────┘
                                   │
                         ┌─────────┴─────────┐
                         │  Research Tools:  │
                         │  • Company Info   │
                         │  • Competitors    │
                         │  • Business Model │
                         │  • Keywords       │
                         └───────────────────┘
```

## 📋 Components

### 1. MCP Research Server (`mcp_research_server.py`)
FastMCP server providing research tools:
- `search_company_info()` - Search for basic company information
- `find_competitors()` - Find competitor companies
- `analyze_company_business()` - Analyze business model and activities
- `extract_market_keywords()` - Extract market and industry keywords
- `generate_competitive_report()` - Generate full competitive analysis

### 2. Gradio Application (`gradio_app.py`)
Interactive web interface that:
- Accepts company name and OpenAI API key as inputs
- Orchestrates MCP tool calls for data gathering
- Uses OpenAI to generate intelligent summaries
- Displays results in an organized, user-friendly format

## 🚀 Quick Start

### Prerequisites

- Python 3.8 or higher
- OpenAI API key ([Get one here](https://platform.openai.com/api-keys))

### Installation

1. **Clone or download this repository**

2. **Run the setup script**:
   ```bash
   chmod +x setup.sh
   ./setup.sh
   ```

3. **Configure your API key**:
   ```bash
   cp .env.example .env
   # Edit .env and add your OpenAI API key
   ```

### Manual Installation

If you prefer manual setup:

```bash
# Create virtual environment
python3 -m venv venv
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt
```

## 💻 Usage

### Start the Application

```bash
# Activate virtual environment (if not already active)
source venv/bin/activate

# Run the Gradio app
python gradio_app.py
```

The application will start on `http://localhost:7860`

### Using the Interface

1. **Enter a company name** (e.g., "Apple", "Tesla", "Netflix")
2. **Enter your OpenAI API key** (required for AI analysis)
3. **Click "Research Company"** to start the analysis
4. **View results**:
   - Executive Summary (AI-generated)
   - Full Report (expand accordion)
   - Market Keywords (expand accordion)

### Example Companies to Try

- **Technology**: Apple, Microsoft, Google, Amazon, Meta
- **Automotive**: Tesla, Ford, General Motors
- **Entertainment**: Netflix, Disney
- **Consumer Goods**: Nike, Coca-Cola, Starbucks

## 📦 Dependencies

- **fastmcp** - Model Context Protocol server framework
- **gradio** - Web UI framework
- **openai** - OpenAI API client
- **requests** - HTTP library for web requests
- **beautifulsoup4** - HTML parsing (for future web scraping)
- **python-dotenv** - Environment variable management

## 🔧 How It Works

1. **User Input**: User enters company name in Gradio interface
2. **MCP Tools**: Application calls MCP research tools to gather data:
   - Company information from Wikipedia API
   - Competitor identification from database
   - Business model analysis
   - Market keyword extraction
3. **AI Synthesis**: OpenAI GPT-4 processes all research data and generates:
   - Executive summary
   - Key insights
   - Market positioning analysis
4. **Results Display**: Formatted report shown in Gradio UI

## 🎯 Use Cases

- **Competitive Intelligence**: Understand your competitors quickly
- **Market Research**: Identify market trends and keywords
- **Investment Analysis**: Research companies for investment decisions
- **Business Strategy**: Inform strategic planning with competitive data
- **Sales Enablement**: Prepare for sales conversations with prospect research

## 🔐 Security Notes

- Never commit your `.env` file or expose your OpenAI API key
- Use environment variables for sensitive information
- The `.env.example` file is provided as a template

## 🛠️ Customization

### Adding More Companies

Edit `mcp_research_server.py` and add entries to the data dictionaries:
- `competitors_db` (line ~70)
- `business_data` (line ~100)
- `industry_keywords` (line ~140)

### Using Real APIs

For production use, replace the sample data with real API calls:
- Business data APIs (Crunchbase, PitchBook)
- Financial APIs (Alpha Vantage, Yahoo Finance)
- News APIs (NewsAPI, Google News)
- Web scraping (requests + BeautifulSoup)

### Changing OpenAI Model

In `gradio_app.py`, modify the model parameter:
```python
model="gpt-4o-mini"  # Change to "gpt-4o", "gpt-4-turbo", etc.
```

## 📊 Project Structure

```
mcp2_test/
├── README.md                    # This file
├── requirements.txt             # Python dependencies
├── .env.example                 # Environment variables template
├── setup.sh                     # Setup script
├── mcp_research_server.py       # MCP server with research tools
└── gradio_app.py               # Gradio web application
```

## 🐛 Troubleshooting

### "Module not found" errors
```bash
pip install -r requirements.txt
```

### "Invalid API key" error
- Check your OpenAI API key in the input field
- Ensure you have credits in your OpenAI account
- Verify the key starts with `sk-`

### Port already in use
Change the port in `gradio_app.py`:
```python
demo.launch(server_port=7861)  # Use different port
```

## 🚀 Future Enhancements

- [ ] Real-time web scraping for live data
- [ ] Integration with business intelligence APIs
- [ ] Export reports to PDF/CSV
- [ ] Historical trend analysis
- [ ] Multi-company comparison view
- [ ] Financial metrics integration
- [ ] News sentiment analysis
- [ ] Custom report templates

## 📝 License

This project is provided as-is for educational and research purposes.

## 🤝 Contributing

Contributions welcome! Feel free to:
- Add more MCP tools
- Improve the UI/UX
- Integrate additional APIs
- Enhance the AI prompts
- Add export functionality

## 💡 Learn More

- [FastMCP Documentation](https://github.com/jlowin/fastmcp)
- [Gradio Documentation](https://gradio.app/docs)
- [OpenAI API Reference](https://platform.openai.com/docs)
- [Model Context Protocol](https://modelcontextprotocol.io)

---

**Built with ❤️ using FastMCP, OpenAI, and Gradio**