# Benchmark MCP Server
MCP Server with Industry Benchmarking Tool - **Compatible with both Claude and ChatGPT**.
## Features
- 📊 **Industry Benchmarking Tool**: Compare company metrics against industry averages
- 🎨 **Interactive Widget**: Visual bar chart comparison (MCP Apps)
- 🔄 **Dual Transport**: Supports both SSE and Streamable HTTP
- ✅ **Cross-Platform**: Works with Claude.ai and ChatGPT
## Quick Start
### With Poetry (Recommended)
```bash
# Install dependencies
poetry install
# Start server
poetry run python main.py
```
### With pip
```bash
# Create virtual environment
python -m venv venv
source venv/bin/activate # or `venv\Scripts\activate` on Windows
# Install dependencies
pip install mcp>=1.26.0 uvicorn pydantic
# Start server
python main.py
```
## Endpoints
| Endpoint | Transport | Use For |
|----------|-----------|---------|
| `/sse` | SSE | Claude, ChatGPT (via ngrok) |
| `/v1/mcp` | Streamable HTTP | ChatGPT native |
| `/mcp` | Streamable HTTP | Alias |
## Usage with ngrok
```bash
# Start ngrok
ngrok http 8000
# Use the ngrok URL in Claude/ChatGPT:
# https://your-ngrok-url/sse
```
## Project Structure
```
claude-mcp-app/
├── app/
│ ├── service/
│ │ ├── mcp_server.py # FastMCP instance
│ │ ├── data/ # Mock benchmark data
│ │ ├── tools/ # MCP tools
│ │ │ ├── benchmarking_tool.py
│ │ │ └── benchmarking_widget.py
│ │ └── widgets/ # HTML widgets
│ │ └── benchmarking_widget.html
├── common/
│ └── config.py # Configuration
├── main.py # Entry point
├── pyproject.toml # Poetry config
└── README.md
```
## Example Prompts
- "How does my restaurant's $45,000 yearly profit compare to the industry average in California?"
- "Compare my retail business revenue of $500,000 against industry benchmarks in Texas"
- "Benchmark my healthcare company's monthly income of $80,000 against regional averages"
- "How does my construction company in NY with $600,000 annual revenue compare?"
## License
MIT
