fashion-inventory-mcp
Uses OpenAI's language models to interpret natural-language shopping queries and generate outfit recommendations based on real inventory data.
Provides cloud deployment for the MCP server, making the inventory search and AI agent accessible via a public endpoint.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fashion-inventory-mcpfind me a black waterproof jacket in medium under 150 euros"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Project 1: Fashion Inventory MCP Cloud Agent
This project is deployed on Railway. It owns the inventory flat file, searches it, and uses OpenAI to interpret natural-language shopping requirements.
Important files
cloud_agent.py: MCP server, inventory search tools, and cloud AI agent.data/inventory.json: 930 fictional fashion items across 31 categories.generate_inventory.py: reproducibly rebuilds the inventory file.railway.json: Railway start command..env.example: required variable names without real secrets.
Related MCP server: Shopify MCP
Cloud AI role
The cloud AI translates language such as "black waterproof-style jacket in medium
under 150 euros" into arguments for search_inventory. Python—not AI—filters the
flat file and returns exact products, prices, sizes, and stock. The AI then selects
and explains matches without inventing inventory.
It also exposes recommend_matching_items. For a question such as "what trousers go
with a navy shirt?", the cloud AI obtains approved color pairings, searches real
trouser stock, and returns only available SKUs.
Run locally on Mac
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt
cp .env.example .envAdd real values to .env, then:
python cloud_agent.pyThe local test endpoint is http://127.0.0.1:8000/mcp.
Deploy on Railway
Push the parent repository to GitHub and create a Railway service. Because this is a subfolder, configure:
Root Directory: /fashion-inventory-system/cloud-inventory-mcp
Config File Path: /fashion-inventory-system/cloud-inventory-mcp/railway.jsonAdd Railway variables:
MCP_SECRET_TOKEN=your-generated-shared-secret
OPENAI_API_KEY=your-cloud-openai-key
CLOUD_OPENAI_MODEL=gpt-4.1-miniDo not define PORT; Railway supplies it. Generate a public domain. The MCP endpoint
will be https://YOUR-SERVICE.up.railway.app/mcp.
See the parent OVERVIEW_AND_SETUP.md for the complete two-project walkthrough.
git status git add cloud_agent.py generate_inventory.py data/inventory.json README.md git commit -m "Add complete catalog and outfit recommendations" git push origin main
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/hemantmnl/fashion-inventory-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server