
FastMCP_RecSys
A CLIP-Based Fashion Recommender system that allows users to upload clothing images and receive tags and recommendations based on visual analysis.
README
FastMCP_RecSys
This is a CLIP-Based Fashion Recommender with MCP.
Folder Structure
/project-root
│
├── /backend
│ ├── Dockerfile # Backend Dockerfile
│ ├── /app
│ │ ├── main.py # FastAPI app code
│ │ └── requirements.txt # Python dependencies for the backend
│ └── .env # Environment variables (make sure to add this to .gitignore)
│
├── /frontend
│ ├── Dockerfile # Frontend Dockerfile
│ ├── package.json # Node.js dependencies (for React)
│ ├── package-lock.json # Lock file for React dependencies
│ ├── /public
│ │ └── index.html # HTML file for the frontend (React app is mounted here)
│ ├── /src
│ │ ├── App.js # Main React component
│ │ └── index.js # React entry point
│ ├── tailwind.config.js # Tailwind CSS config
│ ├── postcss.config.js # PostCSS config
│ └── .env # Frontend environment variables (add to .gitignore)
│
├── .gitignore # Git ignore file (include .env, node_modules, etc.)
├── docker-compose.yml # Docker Compose configuration
└── README.md # Project documentation
Step 1
Update mongo service to add the same credentials:
mongo:
image: mongo:latest
ports:
- "27017:27017"
environment:
MONGO_INITDB_ROOT_USERNAME: root
MONGO_INITDB_ROOT_PASSWORD: example
volumes:
- mongo-data:/data/db
Note: Since using environment variables in the FastAPI app, the Mongo URL should look like this: MONGO_URL = "mongodb://root:example@mongo:27017"
Once it's running, open the browser and go to 👉 http://localhost:8081
Login with: Username: root / Password: example (temporarily setting)
Step 2
docker-compose up --build
This will:
- Start FastAPI backend with hot reload
- Start MongoDB
- Start Mongo Express (for DB UI) (Frontend will not be built automatically in this mode)
Step 3
- Access the frontend (React app) at: http://localhost:3000
- Access the backend (FastAPI app) at: http://localhost:8000
📌 Quick Tips
Visit your app at: http://localhost:8000/docs
View MongoDB UI: http://localhost:8081 (use user: root, password: example)
mongo-seed runs only once at startup to populate your tags collection.
📌 Sample Components for UI
- Image upload
- Submit button
- Display clothing tags + recommendations
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.