Skip to main content
Glama

FastMCP_RecSys

by attarmau

FastMCP_RecSys

This is a CLIP-Based Fashion Recommender with MCP.

Mockup

A user uploads a clothing image โ†’ YOLO detects clothing โ†’ CLIP encodes โ†’ Recommend similar

Folder Structure

/project-root โ”‚ โ”œโ”€โ”€ /backend โ”‚ โ”œโ”€โ”€ Dockerfile โ”‚ โ”œโ”€โ”€ /app โ”‚ โ”‚ โ”œโ”€โ”€ server.py # FastAPI app code โ”‚ โ”‚ โ”œโ”€โ”€ /routes โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ clothing_routes.py โ”‚ โ”‚ โ”œโ”€โ”€ /controllers โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ clothing_controller.py โ”‚ โ”‚ โ”‚ โ””โ”€โ”€clothing_tagging.py โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ tag_extractor.py # Pending: define core CLIP functionality โ”‚ โ”‚ โ”œโ”€โ”€ schemas/ โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ clothing_schemas.py โ”‚ โ”‚ โ”œโ”€โ”€ config/ โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ tag_list_en.py $ Tool for mapping: https://jsoncrack.com/editor โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ database.py โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ settings.py โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ api_keys.py โ”‚ โ”‚ โ””โ”€โ”€ requirements.txt โ”‚ โ””โ”€โ”€ .env โ”‚ โ”œโ”€โ”€ /fastmcp โ”‚ โ””โ”€โ”€ app โ”‚ โ””โ”€โ”€ server.py โ”‚ โ”œโ”€โ”€ /frontend โ”‚ โ”œโ”€โ”€ Dockerfile โ”‚ โ”œโ”€โ”€ package.json โ”‚ โ”œโ”€โ”€ package-lock.json โ”‚ โ”œโ”€โ”€ /public โ”‚ โ”‚ โ””โ”€โ”€ index.html โ”‚ โ”œโ”€โ”€ /src โ”‚ โ”‚ โ”œโ”€โ”€ /components โ”‚ โ”‚ โ”‚ โ”œโ”€โ”€ ImageUpload.jsx โ”‚ โ”‚ โ”‚ โ”œโ”€โ”€ DetectedTags.jsx โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ Recommendations.jsx โ”‚ โ”‚ โ”œโ”€โ”€ /utils โ”‚ โ”‚ โ”‚ โ””โ”€โ”€ api.js โ”‚ โ”‚ โ”œโ”€โ”€ App.js # Main React component โ”‚ โ”‚ โ”œโ”€โ”€ index.js โ”‚ โ”‚ โ”œโ”€โ”€ index.css โ”‚ โ”‚ โ”œโ”€โ”€ tailwind.config.js โ”‚ โ”‚ โ”œโ”€โ”€ postcss.config.js โ”‚ โ”‚ โ””โ”€โ”€ .env โ”‚ โ”œโ”€โ”€ .gitignore โ”‚ โ”œโ”€โ”€ docker-compose.yml โ”‚ โ””โ”€โ”€ README.md โ””โ”€โ”€โ”€โ”€โ”€โ”€ requirements.txt

Quick Start Guide

Step 1: Clone the GitHub Project

Step 2: Set Up the Python Environment

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

Step 3: Install Dependencies

pip install -r requirements.txt

Step 4: Start the FastAPI Server (Backend)

uvicorn backend.app.server:app --reload

Once the server is running and the database is connected, you should see the following message in the console:

Database connected INFO: Application startup complete.

Step 5: Install Dependencies

Database connected INFO: Application startup complete.

npm install

Step 6: Start the Development Server (Frontend)

npm start

Once running, the server logs a confirmation and opens the app in your browser: http://localhost:3000/

๐Ÿ“Œ Sample Components for UI

  1. Image upload

  2. Submit button

  3. Display clothing tags + recommendations

Whatโ€™s completed so far:

  1. FastAPI server is up and running (24 Apr)

  2. Database connection is set up (24 Apr)

  3. Backend architecture is functional (24 Apr)

  4. Basic front-end UI for uploading picture (25 Apr)

Next Step:

  1. Evaluate CLIPโ€™s tagging accuracy on sample clothing images

  2. Fine-tune the tagging system for better recommendations

  3. Test the backend integration with real-time user data

  4. Set up monitoring for model performance

  5. Front-end demo

-
security - not tested
-
license - not tested
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A CLIP-Based Fashion Recommender system with MCP that provides fashion recommendations based on uploaded images.

  1. Mockup
    1. Folder Structure
      1. Quick Start Guide
    2. Whatโ€™s completed so far:

      Related MCP Servers

      • A
        security
        -
        license
        A
        quality
        An MCP server that integrates FindMine's product styling and outfit recommendation capabilities with Claude and other MCP-compatible applications, allowing users to browse products, get outfit recommendations, find similar items, and access style guidance.
        Last updated -
        3
        26
        1
      • -
        security
        -
        license
        -
        quality
        A CLIP-Based Fashion Recommender system that allows users to upload clothing images and receive tags and recommendations based on visual analysis.
        Last updated -
        Apache 2.0
        • Linux
        • Apple
      • -
        security
        -
        license
        -
        quality
        A TypeScript-based MCP server that implements virtual try-on capabilities using the HeyBeauty API, allowing users to visualize how clothes would look on them through Claude.
        Last updated -
        13
        19
        MIT License
        • Apple
      • A
        security
        -
        license
        A
        quality
        An MCP server that exposes Fabric patterns as tools for Cline, enabling AI-driven pattern execution directly within Cline tasks.
        Last updated -
        1
        13
        MIT License
        • Apple
        • Linux

      View all related MCP servers

      MCP directory API

      We provide all the information about MCP servers via our MCP API.

      curl -X GET 'https://glama.ai/api/mcp/v1/servers/attarmau/StyleCLIP'

      If you have feedback or need assistance with the MCP directory API, please join our Discord server