Fashion Recommendation System MCP server

FastMCP_RecSys is a CLIP-based fashion recommendation system that detects clothing items in uploaded images and recommends similar products. The system uses computer vision to identify clothing items, encode them with CLIP, and then find visually similar items to recommend to users.

Installation

Prerequisites

Before installing the system, ensure you have Python installed on your machine.

Setting Up the Environment

1. Clone the repository:

   git clone [repository-url]
   cd FastMCP_RecSys
   

2. Create and activate a virtual environment:

   python -m venv venv
   
   # On macOS or Linux
   source venv/bin/activate
   
   # On Windows
   venv\Scripts\activate
   

3. Install dependencies:

   pip install -r requirements.txt
   

Running the Server

Starting the Backend

To run the FastAPI backend server:

uvicorn backend.app.server:app --reload

You should see a confirmation message when the server starts successfully:

Database connected
INFO:     Application startup complete.

The backend API will be available at http://localhost:8000.

Starting the Frontend

To run the frontend development server:

1. Install Node.js dependencies:

   cd frontend
   npm install
   

2. Start the frontend server:

   npm start
   

The application will automatically open in your browser at http://localhost:3000.

Using the Application

Uploading Images

1. Navigate to the main page of the application.
2. Use the image upload component to select a clothing image from your device.
3. Click the "Submit" button to process the image.

Viewing Results

After uploading and processing an image:

1. The system will detect clothing items in the image
2. It will display tags identifying the clothing items
3. You'll see recommendations for similar clothing items

API Endpoints

The backend provides RESTful API endpoints for clothing recommendations. You can access the API documentation at http://localhost:8000/docs once the server is running.

Troubleshooting

If you encounter issues connecting to the database, verify your database configuration in the .env file in the backend directory.

For other technical issues, check the server logs which will display any errors during operation.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.