Skip to main content
Glama
Aqillz

Alexa+ Enterprise Hub

by Aqillz

🧠 Alexa+ Enterprise Hub (Small Business Inventory MCP)

Built for the Build, Ship, Shape: Amazon Developer Hackathon (Alexa+ Track).

The Alexa+ Enterprise Hub is a self-hosted Model Context Protocol (MCP) server and simulated Alexa+ web client. It is engineered to bring enterprise-grade supply chain intelligence to small shopkeepers, hawker stalls, and local cafe owners through intuitive conversational AI.


🌟 Inspiration & What It Does

Small businesses constantly fight a battle against dead capital and inventory spoilage. Relying on manual tracking makes predicting stockouts difficult and time-consuming.

The Alexa+ Enterprise Hub acts as an autonomous supply chain assistant. It tracks dynamic daily burn rates, predicts imminent stockouts, and proactively helps manage vendor relationships through simple conversational commands.


Related MCP server: Sales and Stock Analysis MCP Server

✨ Key Features (MCP Tools)

  • Predictive Stockouts & Spoilage Logging: Tracks dynamic daily burn rates and warns owners before high-velocity staples run out or perishables expire.

  • Automated Purchase Orders: Automatically aggregates low-stock items by supplier and generates dispatch-ready Purchase Order (PO) payloads.

  • Smart Budget Planning: Simulates the most critical reorders needed to stay operational under strict cash-flow constraints.

  • Clearance Engine: Scans for near-expiry items and automatically generates promotional markdown strategies to recoup costs.

  • Profit Projections & Custom Items: Seamlessly adds new items directly to the database and calculates projected profit margins based on wholesale costs and retail markups.


πŸ—οΈ Architecture & Compliance

This project strictly adheres to the official hackathon requirements for the Alexa+ simulated experience path:

  • server.py (Backend): A FastAPI server fully compliant with the 2025-11-25 Streamable HTTP MCP specification. It exposes over 15 specialized enterprise tools via JSON-RPC.

  • index.html (Simulated Client): A browser-based Agentic Chat Simulator and GUI dashboard that executes conversational commands against the backend tools in real-time.

  • inventory_seed.json: A flexible data seed file that automatically populates the live SQLite database (inventory.db) on the first boot.


πŸš€ Quick Start Instructions

1. Install Dependencies

Ensure you have Python installed, then install the required FastAPI and Uvicorn packages:

pip install fastapi uvicorn

2. Run the Server

Launch the MCP server and web dashboard:

python server.py

3. Open the Dashboard

Open your web browser and navigate to:

http://127.0.0.1:8000

4. Test the Agent

Try typing these sample prompts into the Agentic Chat Simulator, or click the guided prompt cards on the user interface:

  • "Add new item KFC Bucket, Fast Food, 15, buckets, 5, 2, 2026-10-31, KFC Corp, $12.50"

  • "Simulate reorder budget for $150"

  • "Calculate profit projection at 40% markup"


πŸ“„ License

This project is licensed under the MIT License.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables natural-language queries of retail sell-through, inventory coverage, out-of-stock risk, and reorder suggestions from POS and warehouse data, with an optional agent that emails reorder proposals.
    58 npm
    MIT
  • A
    license
    A
    quality
    B
    maintenance
    Enables AI agents to manage inventory conversationally: list and look up products, check current stock levels, record inbound and outbound movements idempotently, review movement history, and surface items below their minimum threshold. Every figure is grounded in tool calls rather than model estimation, and invalid operations return explicit error codes the agent can reason about.
    5
    MIT