BIM Electrical MCP

BIM Electrical MCP is a Python-based application for processing electrical BIM data from DXF and Revit-style JSON files, sanitizing and storing the extracted information in a Supabase database, and enabling AI-assisted querying through a conversational assistant.

The project is designed to help teams manage and analyze electrical design data more efficiently by combining file processing, structured storage, and intelligent chat-based interaction.

Key Features

• Upload and process DXF and JSON BIM files

• Extract electrical components and related metadata

• Sanitize and redact sensitive or non-essential information before storage

• Store processed data in Supabase using a structured schema

• Query data through an AI-powered Electrical Chat Assistant powered by Google Gemini

• Support a modular architecture for future integrations and extensions

Related MCP server: mcp-server-for-revit

Tech Stack

• Python

• Streamlit

• Supabase

• Google Gemini API

• Additional libraries such as ezdxf, pandas, pydantic, python-dotenv, and pytest

Project Structure

.
├── app.py                     # Main Streamlit application entry point
├── requirements.txt          # Python dependencies
├── .env.example              # Example environment configuration template
├── src/
│   ├── agent/                # AI assistant integration logic
│   ├── db/                   # Supabase client and SQL schema
│   ├── extractors/           # DXF and JSON extraction logic
│   ├── mcp_server/           # MCP server-related components
│   ├── sanitizer/            # Data sanitization/redaction utilities
│   └── ui/                   # Pipeline and UI orchestration helpers
├── tests/                    # Unit and integration tests
└── TDD.md                    # Development/testing notes

Getting Started

1. Clone the repository

git clone <your-repository-url>
cd bim-electrical-mcp

2. Create and activate a virtual environment

On Windows:

python -m venv venv
venv\Scripts\activate

On macOS/Linux:

python3 -m venv venv
source venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Configure environment variables

Create a .env file in the project root by copying the example template:

copy .env.example .env

Or on macOS/Linux:

cp .env.example .env

Then update the values in .env with your own generic configuration. The file should include the required Supabase and Google Gemini settings, for example:

SUPABASE_URL=https://your-project.supabase.co
SUPABASE_ANON_KEY=your-anon-key
SUPABASE_SERVICE_KEY=your-service-key
GOOGLE_API_KEY=your-google-api-key
GOOGLE_PROJECT_ID=your-google-project-id
GOOGLE_LOCATION=global

Keep credentials and sensitive values private and never commit the .env file to a public repository.

Database Setup

This project uses Supabase as its data store. After creating a Supabase project:

1. Open the SQL Editor in Supabase.

2. Execute the SQL from src/db/schema.sql.

3. Ensure the required PostgreSQL extensions are available, including vector and pgcrypto.

The schema creates the core tables used by the application, including components and connections.

Running the Application

Start the Streamlit app with:

streamlit run app.py

Then open the local Streamlit URL in your browser to upload files, process BIM data, and interact with the assistant.

Testing

To run the test suite:

pytest

License

This project is intended for educational, internal, or open-source use. Please review and adjust licensing terms as needed before distribution.