Skip to main content
Glama

MCP Product Management System

by pysorflow
GitHub
Python
  • Apple
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

๐Ÿ›๏ธ MCP Product Management System

A comprehensive Model Context Protocol (MCP) server for product inventory management with PostgreSQL database backend, Docker containerization, and multiple AI platform integrations.

๐ŸŽฏ System Overview

This system provides a sophisticated product management platform with:

  • 9,739 products across multiple categories

  • 9 advanced MCP tools with Django-style filtering

  • PostgreSQL database with Docker containerization

  • Multi-platform AI integration (Claude Desktop, Ollama, Perplexity)

  • Advanced filtering & pagination capabilities

  • Natural language query processing

๐Ÿ—๏ธ Architecture

โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ Claude Desktopโ”‚ โ”‚ MCP Inspector โ”‚ โ”‚ Ollama โ”‚ โ”‚ Perplexity โ”‚ โ”‚ โ”‚ โ”‚ โ”‚ โ”‚ Bridge โ”‚ โ”‚ Local โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚ โ”‚ โ”‚ โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ผโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚ โ”‚ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ โ”‚ Local MCP Server โ”‚ โ”‚ โ”‚ (local_mcp_server.py) โ”‚ โ”‚ โ”‚ โ€ข 9 Advanced Tools โ”‚ โ”‚ โ”‚ โ€ข Django Filtering โ”‚ โ”‚ โ”‚ โ€ข Pagination โ”‚ โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚ โ”‚ โ”‚ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ โ”‚ Docker MCP Server โ”‚ โ”‚ โ”‚ (mcp_server.py) โ”‚ โ”‚ โ”‚ โ€ข Container-based โ”‚ โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ฌโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜ โ”‚ โ”‚ โ”‚ โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”ดโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ โ”‚ PostgreSQL DB โ”‚โ—„โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€-โ”˜ โ”‚ โ€ข 9,739 products โ”‚ Direct Connection โ”‚ โ€ข Full-text search โ”‚ (ollama_mcp_bridge.py) โ”‚ โ€ข Advanced indexes โ”‚ โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜

๐Ÿ› ๏ธ Setup & Installation

Prerequisites

  • Docker & Docker Compose

  • Python 3.10+ (required for MCP library)

  • Node.js (for MCP Inspector)

  • Ollama (optional, for Ollama integration)

๐Ÿ” Python Version Check

# Check your Python version first python3 --version # If you have Python < 3.10, you need to upgrade or use a different Python version # On macOS with Homebrew: # brew install python@3.11 # On Ubuntu/Debian: # sudo apt update && sudo apt install python3.11 # On Windows: Download from python.org

1. Clone & Setup

git clone https://github.com/pysorflow/mcpdemo.git cd mcpdemo # Create Python virtual environment (use Python 3.10+) python3 -m venv venv source venv/bin/activate # On macOS/Linux # venv\Scripts\activate # On Windows # If python3 is too old, try specific version: # python3.11 -m venv venv # python3.10 -m venv venv # Install dependencies pip install -r requirements.txt

2. Start Docker Services

# Start PostgreSQL database docker-compose up -d # Verify services are running docker-compose ps

3. Import Product Data

# Import 9,739 products into database python import_products.py

4. Test System

# Run comprehensive tests python test.py

๐Ÿ”ง Available MCP Tools

Core Tools

  1. get_product - Get detailed product information by SKU

  2. list_products - List products with optional category filtering

  3. search_products - Basic search across product fields

  4. advanced_search_products - Comprehensive search with filtering

  5. update_stock - Update product stock levels

Advanced Tools

  1. filter_products - Django-style filtering with pagination

    • Field lookups: category__icontains, stock__gte, price__lte, etc.

    • Sorting: ["-stock", "title"]

    • Pagination: page, page_size

  2. get_categories - List all product categories and subcategories

  3. get_low_stock_products - Find products with low inventory

  4. get_filter_stats - Get filtering statistics and breakdowns

Django-Style Filter Examples

{ "filters": { "category__icontains": "shirt", "color__icontains": "blue", "stock__gte": 50, "price__lte": 25.00, "size__in": ["L", "XL"] }, "ordering": ["-stock", "price"], "page": 1, "page_size": 20 }

๐Ÿ–ฅ๏ธ Platform Integration

1. MCP Inspector (Testing & Development)

Setup & Run

# Install MCP Inspector globally npm install -g @modelcontextprotocol/inspector # Start local MCP server + Inspector npx @modelcontextprotocol/inspector python local_mcp_server.py

Usage

  • URL: Opens automatically in browser (usually http://localhost:5173)

  • Features: Test all 9 tools, view JSON schemas, debug responses

  • Best for: Development, testing, debugging MCP tools

2. Claude Desktop Integration

Setup Configuration

  1. Locate Claude Desktop config file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

    • Windows: %APPDATA%\Claude\claude_desktop_config.json

  2. Add MCP server configuration:

{ "mcpServers": { "product-manager": { "command": "/Users/arunss/Documents/myroot/mcpdemo/run_mcp_server.sh", "args": [] } } }

  1. Make shell script executable:

chmod +x run_mcp_server.sh

Usage

  • Restart Claude Desktop after config changes

  • Natural language queries: "Show me blue shirts under $20 with good stock"

  • Complex filtering: "Find size XL products sorted by price"

  • Business queries: "What are our top categories by inventory?"

Example Queries

  • "Give me details of SKU 120715"

  • "Show products with more than 1000 units in stock"

  • "What black items do we have from Gildan warehouse?"

  • "Filter polo shirts with prices between $15 and $30"

3. Ollama Integration

Setup Ollama

# Install Ollama curl -fsSL https://ollama.ai/install.sh | sh # Download recommended models ollama pull qwen2.5:7b-instruct # Best for natural language ollama pull llama3.2:1b # Fastest, lightweight ollama pull llama3.1:8b # Balanced performance

Run Ollama Bridge

# Start enhanced Ollama bridge python ollama_mcp_bridge.py

Features

  • Model selection at startup

  • Natural language processing with LLM-based query parsing

  • Advanced filtering through conversational interface

  • Statistics commands: stats, examples, models

Usage Example

๐Ÿ’ฌ Your question [qwen2.5:7b-instruct]: Show me blue shirts under $20 with good stock ๐Ÿ” Analyzing: 'Show me blue shirts under $20 with good stock' ๐ŸŽฏ Initial classification: ADVANCED_FILTER ๐Ÿค– LLM filter analysis: {"filters": {"color__icontains": "blue", "category__icontains": "shirt", "price__lte": 20, "stock__gte": 50}, "ordering": ["-stock"], "page_size": 10} ๐Ÿ“Š Data retrieved: 1247 characters ๐Ÿค– Answer: Based on your search for blue shirts under $20 with good stock, I found several excellent options...

4. Perplexity Local Integration

Setup

  1. Install Perplexity Desktop or use Perplexity API

  2. Configure MCP connection in Perplexity settings

  3. Add server endpoint:

{ "mcp_servers": { "product_manager": { "type": "local", "command": "python", "args": ["/Users/arunss/Documents/myroot/mcpdemo/local_mcp_server.py"], "working_directory": "/Users/arunss/Documents/myroot/mcpdemo" } } }

Usage

  • Research queries: "Analyze our product inventory distribution"

  • Business intelligence: "What's our stock situation across categories?"

  • Data exploration: "Show me patterns in our product pricing"

๐Ÿ“‹ Usage Workflows

Development Workflow

  1. Start Docker: docker-compose up -d

  2. Test with Inspector: npx @modelcontextprotocol/inspector python local_mcp_server.py

  3. Debug tools, test filters, verify responses

  4. Deploy to AI platforms

Production Workflow

  1. Docker services running: docker-compose up -d

  2. Claude Desktop configured with shell script

  3. Ollama bridge available for advanced NLP

  4. Multiple access points for different use cases

Business User Workflow

  1. Open Claude Desktop

  2. Ask natural language questions:

    • "What's our inventory status?"

    • "Show me slow-moving products"

    • "Find products that need restocking"

  3. Get instant, detailed responses

๐Ÿ” Sample Questions & Use Cases

Basic Queries

  • "Give me details of product SKU 120715"

  • "List all T-shirt categories we have"

  • "Show me products with low stock"

Advanced Filtering

  • "Show blue shirts under $20 with good stock levels"

  • "Find size XL products sorted by price ascending"

  • "What black items do we have from Gildan warehouse?"

Business Intelligence

  • "What are our top 5 categories by product count?"

  • "Show me inventory distribution across warehouses"

  • "Which products have the highest stock levels?"

Inventory Management

  • "Products with more than 1000 units in stock"

  • "Show items that are running low on inventory"

  • "What's our most expensive product in each category?"

Complex Analysis

  • "Filter polo shirts with prices between $15 and $30"

  • "Show me all products from Hanes with sizes L and XL"

  • "Find products with zero stock sorted by category"

๐Ÿงช Testing

Run Test Suite

python test.py

Test Individual Components

# Test database connection python -c "import psycopg2; print('DB OK')" # Test MCP server python local_mcp_server.py # Test Ollama bridge python ollama_mcp_bridge.py

Verification Checklist

  • โœ… Docker services running (docker-compose ps)

  • โœ… Database populated (9,739 products)

  • โœ… MCP tools functional (test.py passes)

  • โœ… Claude Desktop integration working

  • โœ… Ollama models available

๐Ÿ“ File Structure

mcpdemo/ โ”œโ”€โ”€ ๐Ÿ“„ README.md # This comprehensive guide โ”œโ”€โ”€ ๐Ÿณ docker-compose.yml # Docker services configuration โ”œโ”€โ”€ ๐Ÿณ Dockerfile # MCP server container โ”œโ”€โ”€ ๐Ÿ“‹ requirements.txt # Python dependencies โ”œโ”€โ”€ ๐Ÿ› ๏ธ local_mcp_server.py # Main MCP server (9 tools) โ”œโ”€โ”€ ๐Ÿ› ๏ธ mcp_server.py # Docker-based MCP server โ”œโ”€โ”€ ๐Ÿค– ollama_mcp_bridge.py # Enhanced Ollama integration โ”œโ”€โ”€ ๐Ÿ“Š import_products.py # Data import script โ”œโ”€โ”€ ๐Ÿงช test.py # Comprehensive test suite โ”œโ”€โ”€ ๐Ÿ“ sample_questions.txt # 25 sample questions + examples โ”œโ”€โ”€ โš™๏ธ run_mcp_server.sh # Claude Desktop shell script โ”œโ”€โ”€ โš™๏ธ claude_desktop_config.json # Claude Desktop configuration โ”œโ”€โ”€ ๐Ÿ“ฆ products-master.csv # Product data (9,739 items) โ””โ”€โ”€ ๐Ÿ“ venv/ # Python virtual environment

โš ๏ธ Troubleshooting

Common Issues

1. Database Connection Failed

# Check Docker services docker-compose ps # Restart if needed docker-compose down && docker-compose up -d

2. Python Version Error (MCP requires Python 3.10+)

# Check your Python version python3 --version # If version is < 3.10, upgrade Python: # macOS (Homebrew): brew install python@3.11 # Ubuntu/Debian: sudo apt install python3.11 # Windows: Download from python.org # Create virtual environment with correct Python version python3.11 -m venv venv # or python3.10 source venv/bin/activate pip install -r requirements.txt

3. MCP Server Not Starting

# Check Python environment source venv/bin/activate pip install -r requirements.txt

4. Claude Desktop Not Connecting

  • Verify config file path

  • Check shell script permissions: chmod +x run_mcp_server.sh

  • Restart Claude Desktop after config changes

5. Ollama Models Not Found

# List available models ollama list # Download missing models ollama pull qwen2.5:7b-instruct

๐Ÿš€ Advanced Features

Django-Style Filtering

  • Field lookups: __icontains, __exact, __gte, __lte, __in

  • Pagination: Automatic with page/page_size

  • Sorting: Multi-field with direction control

  • Global search: Across all text fields

Natural Language Processing

  • LLM-powered query parsing in Ollama bridge

  • Intent classification for optimal tool selection

  • Fallback strategies for complex queries

  • Context-aware responses

Performance Optimizations

  • Database indexes on key fields

  • Connection pooling for high-load scenarios

  • Query optimization for large datasets

  • Efficient pagination with offset/limit

๐Ÿ“ˆ Statistics

  • Total Products: 9,739

  • Categories: 15+ major categories

  • MCP Tools: 9 advanced tools

  • Database: PostgreSQL 16

  • Docker Services: 2 containers

  • AI Platforms: 4 integrations

  • Filter Options: 16 Django-style filters

  • Status: โœ… FULLY OPERATIONAL

๐ŸŽฏ Next Steps

  1. Explore Sample Questions: Check sample_questions.txt for 25 comprehensive examples

  2. Customize Tools: Modify MCP tools for your specific needs

  3. Scale Database: Add more products or customize schema

  4. Extend AI Integration: Add more AI platforms or models

  5. Build Applications: Use MCP protocol for custom applications

๐ŸŽ‰ Your MCP Product Management System is ready for production use!

Last updated: August 2025 System tested and verified across all platforms

This server cannot be installed

-
security - not tested
-
license - not tested
-
quality - not tested

How are these scores calculated?

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A comprehensive Model Context Protocol (MCP) server for product inventory management with PostgreSQL database backend, enabling natural language queries for product information across multiple AI platforms.

  1. ๐ŸŽฏ System Overview
    1. ๐Ÿ—๏ธ Architecture
      1. ๐Ÿ› ๏ธ Setup & Installation
        1. Prerequisites
        2. ๐Ÿ” Python Version Check
        3. 1. Clone & Setup
        4. 2. Start Docker Services
        5. 3. Import Product Data
        6. 4. Test System
      2. ๐Ÿ”ง Available MCP Tools
        1. Core Tools
        2. Advanced Tools
        3. Django-Style Filter Examples
      3. ๐Ÿ–ฅ๏ธ Platform Integration
        1. 1. MCP Inspector (Testing & Development)
          1. Setup & Run
          2. Usage
        2. 2. Claude Desktop Integration
          1. Setup Configuration
          2. Usage
          3. Example Queries
        3. 3. Ollama Integration
          1. Setup Ollama
          2. Run Ollama Bridge
          3. Features
          4. Usage Example
        4. 4. Perplexity Local Integration
          1. Setup
          2. Usage
        5. ๐Ÿ“‹ Usage Workflows
          1. Development Workflow
          2. Production Workflow
          3. Business User Workflow
        6. ๐Ÿ” Sample Questions & Use Cases
          1. Basic Queries
          2. Advanced Filtering
          3. Business Intelligence
          4. Inventory Management
          5. Complex Analysis
        7. ๐Ÿงช Testing
          1. Run Test Suite
          2. Test Individual Components
          3. Verification Checklist
        8. ๐Ÿ“ File Structure
          1. โš ๏ธ Troubleshooting
            1. Common Issues
          2. ๐Ÿš€ Advanced Features
            1. Django-Style Filtering
            2. Natural Language Processing
            3. Performance Optimizations
          3. ๐Ÿ“ˆ Statistics
            1. ๐ŸŽฏ Next Steps

              Related MCP Servers

              • db-mcp-tool

                wirdes
                A
                security
                -
                license
                A
                quality
                A powerful Model Context Protocol (MCP) tool for exploring and managing different types of databases including PostgreSQL, MySQL, and Firestore.
                Last updated -
                9
                5
                MIT License

              • MCP MySQL App

                zalab-inc
                -
                security
                -
                license
                -
                quality
                A Model Context Protocol (MCP) server that enables AI assistants to interact with MySQL databases by executing SQL queries and checking database connectivity.
                Last updated -
                MIT License
                • Apple
                • Linux

              • AgentModeofficial

                agentmode
                A
                security
                -
                license
                A
                quality
                An all-in-one Model Context Protocol (MCP) server that connects your coding AI to numerous databases, data warehouses, data pipelines, and cloud services, streamlining development workflow through seamless integrations.
                Last updated -
                3
                • Apple
                • Linux

              • MCP Server for PostgreSQL

                asadudin
                -
                security
                -
                license
                -
                quality
                A Model Context Protocol server implementation that provides a simple interface to interact with PostgreSQL databases, enabling SQL queries, database operations, and schema management through MCP.
                Last updated -

              View all related MCP servers

              New MCP Servers

              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/pysorflow/mcpdemo'

              If you have feedback or need assistance with the MCP directory API, please join our Discord server