MCP Product Management System

MCP Product Management System - Advanced inventory management with AI integration A comprehensive Model Context Protocol (MCP) server for product inventory management featuring PostgreSQL backend, Docker containerization, and multi-platform AI integrations (Claude Desktop, Ollama, Perplexity).

python

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "pysorflow-mcpdemo": {
      "command": "/Users/arunss/Documents/myroot/mcpdemo/run_mcp_server.sh",
      "args": [],
      "env": {
        "ENV": "PLACEHOLDER"
      }
    }
  }
}

You can deploy and use a PostgreSQL-backed MCP server to manage your product inventory with advanced filtering, multiple AI integrations, and a robust command set. This MCP server helps you query, filter, and analyze product data at scale, with tools that support precise stock and category management, powerful search, and Django-style filtering with pagination.

How to use

Start by connecting an MCP client to the server, then use the nine core and advanced tools to manage products, filter with Django-style criteria, and obtain insights on stock, categories, and pricing.

How to install

Prerequisites include containerization and Python support so you can run the server locally and connect clients.

Configuration and integration

The server supports local execution and container-based deployment, plus integrations with external clients. Use the following setup and starting points to run the MCP server and connect from clients.

# Prerequisites
# - Docker & Docker Compose
# - Python 3.10+
# - Node.js (for MCP Inspector)
# - Optional: Ollama for AI models

# 1) Prepare environment and install dependencies
# - Ensure Python is 3.10+ and create a virtual environment
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

# 2) Start Docker services (PostgreSQL and MCP container)
docker-compose up -d

docker-compose ps

# 3) Import product data (9,739 items)
python import_products.py

# 4) Run tests to verify the setup
python test.py

# 5) Connect an MCP client (example via Claude or Ollama integration handled separately)

Usage with MCP clients

Connect to the MCP server from an MCP client that supports HTTP or stdio connections. Use the available tools to fetch product details, list products with optional filtering, perform advanced searches, and manage stock levels.

Tools overview

The server exposes nine core and advanced tools for production-grade product management and querying.

Troubleshooting

If you encounter issues during startup or operation, verify container status, Python version, and connectivity with MCP clients. Restart services if necessary and check that data import completed successfully.

Available tools

get_product

Get detailed product information by SKU.

list_products

List products with optional category filtering.

search_products

Basic search across product fields.

advanced_search_products

Comprehensive search with filtering and sorting.

update_stock

Update product stock levels.

filter_products

Django-style filtering with pagination, field lookups, sorting, and page controls.

get_categories

List all product categories and subcategories.

get_low_stock_products

Find products with low inventory.

get_filter_stats

Get filtering statistics and breakdowns.

Built by

VeilStrat

AI signals for GTM teams