This MCP server is a demonstration wrapper for Retail Intelligence using Microsoft Fabric capabilities. It exposes a local server that can coordinate and orchestrate components related to retail analytics, AI-assisted decision making, and agent-based workflows. You can use the included endpoints and tooling to explore how Fabric services (data integration, big data processing, real-time analytics, and AI agents) can be composed into a retail intelligence workflow. Typical usage involves starting the server, then invoking its endpoints to run sample data pipelines, trigger predictive analytics, or simulate agent-driven actions such as automated claim review or inventory recommendations. The tools emphasize end-to-end flow: scripting instructions to drive tasks, ML packages for data preparation, LLMs for reasoning and response generation, and agents that can initiate actions or call additional services. The demo is designed to illustrate how these layers interoperate within a retail scenario, from data ingestion to actionable insights.

Prerequisites:

• Node.js (v14+ recommended) and npm installed on your system
• Git (optional, for cloning the repository)

Install and run locally:

1. Clone the repository (or download the demo package): git clone https://github.com/brown9804/microsoftcloudessentials-learninghub-fabric-ai-retail-demo.git cd microsoftcloudessentials-learninghub-fabric-ai-retail-demo

2. Install dependencies: npm install

3. Start the server: npm run start

   or if the project defines a script differently, use:

   node server.js

4. Open the demo in your browser (default port 5000 as configured): http://localhost:5000

Notes:

• If PORT is changed in environment variables, ensure the port in your browser URL matches.
• Review any README or config files in the repo for project-specific setup steps such as API keys or fabric workspace configuration.

Tips and common issues:

• Environment variables: The demo uses PORT and NODE_ENV by default. Adjust these in the env block or your runtime environment if needed.
• If the server fails to start, check that Node.js dependencies are installed and that there are no port conflicts on your machine.
• For Fabric-related features, ensure you have access to the required Fabric services or mock implementations when running offline.
• If you plan to customize the demo, consider modifying the server.js or related route handlers to point to your own data sources or AI models.
• The npm_package field indicates the npm package name to reference for this MCP server; in this setup it is set to fabric-ai-retail-demo.