Automotive Data

Este é um projeto MCP (Model Context Protocol) que demonstra a integração entre um modelo de IA generativa (Google Gemini) e um banco de dados MariaDB, permitindo realizar análises de dados usando linguagem natural.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "raphamaster-mcp-automotivo": {
      "command": "python",
      "args": [
        "src/mcp_gemini.py"
      ],
      "env": {
        "ENV": "UNSPECIFIED"
      }
    }
  }
}

You can run an MCP server that analyzes automotive data using natural language queries, backed by Docker for the database and a Python component that bridges a generative AI model with MariaDB. This setup lets you ask questions in Portuguese and receive generated SQL queries, executed results, and interpreted insights.

How to use

You interact with the server through an MCP client to ask questions about your data. Start your local MCP server, then connect with the client to issue natural language questions such as revenue totals, top-selling products, or sales performance metrics. The system will translate your natural language questions into SQL, run them against MariaDB, and present the results along with useful interpretations. You can progressively ask more complex questions to test the AI model’s ability to generate correct queries and to analyze results.

How to install

Prerequisites you need before starting:

Docker and Docker Compose installed on your machine
Python 3.10 or newer installed
Git installed

Follow these concrete steps to get the MCP server up and running locally.

git clone https://github.com/raphamaster/projeto-mcp-automotivo.git
cd projeto-mcp-automotivo

docker-compose up -d

pip install -r src/requirements.txt

python src/mcp_gemini.py

Notes and tips

The project includes a MariaDB database setup and a Python script that serves as the bridge to the AI model. If you need to customize data, you can replace the database seed file under database/ with your own dataset.

Troubleshooting

If Docker containers fail to start, check docker logs for the database and the Python bridge to identify missing environment variables or port conflicts.