Bio Preferred MCP Server
A Model Context Protocol server that provides AI agents with access to Bio Preferred product data from a PostgreSQL database, enabling product searches, category listings, and contract management via natural language.
README
Bio Preferred MCP Server
A Model Context Protocol (MCP) server that provides AI agents with access to Bio Preferred product data from a PostgreSQL database.
๐ Quick Start
1. Install Dependencies
pip install -r requirements.txt
2. Start the MCP Server
python run_server_simple.py
3. Configure Claude Desktop
Add this configuration to Claude Desktop โ Settings โ Developer โ MCP:
{
"mcpServers": {
"bio-preferred": {
"command": "/Users/ginugeorge/miniconda3/bin/python",
"args": ["/Users/ginugeorge/Report_mcp/run_server_simple.py"],
"name": "Bio Preferred Database",
"description": "Access to Bio Preferred product database with 9 products and 5 categories"
}
}
}
4. Test with Claude
Ask Claude: "What products are in the Bio Preferred database?"
๐ Available Data
- 9 Products: Biodegradable Soap, Plant-Based Degreaser, Soy-Based Paint, etc.
- 5 Categories: Cleaning Agents, Lubricants, Paints & Coatings, Construction Materials, Office Supplies
- 6 Tables: products, product_categories, category_product_map, acquisition, awards, contract_bio_entry
- 4 Acquisition Records: Contract values and funding agencies
๐ ๏ธ MCP Tools
The server provides 9 tools for AI agents:
Product & Category Tools
search_products- Search for products by namelist_categories- Show all product categories
Contract Management Tools
list_contract_information- List all contract information including acquisition details, contract values, and funding agencieslist_contracts_with_reports- List contracts that have submitted reports with submission details and report countslist_contracts_without_reports- List contracts that have NOT submitted reports yet
Database Tools
list_tables- List all database tablesget_table_schema- Explore table structureexecute_custom_query- Execute custom SQL queries (read-only)
๐ Project Structure
Report_mcp/
โโโ ๐ run_server_simple.py # Main MCP server (Claude-compatible)
โโโ ๐ง database.py # Database connection and utilities
โโโ โ๏ธ config.py # Configuration management
โโโ ๐ run_server.py # Alternative server implementation
โโโ ๐ start_for_chatgpt.py # Easy startup script
โโโ ๐ฆ requirements.txt # Python dependencies
โโโ ๐ tests/ # Test suite
โ โโโ test_all.py # Run all tests
โ โโโ test_database_connection.py
โ โโโ test_local_mcp.py
โ โโโ test_mcp_tools.py
โ โโโ test_chatgpt_integration.py
โโโ ๐ docs/ # Documentation
โโโ CHATGPT_INTEGRATION.md
โโโ CHATGPT_SETUP_GUIDE.md
โโโ CONFIGURATION.md
โโโ TESTING.md
โโโ mcp_config.json
๐งช Testing
Run All Tests
python tests/test_all.py
Individual Tests
# Test database connection
python tests/test_database_connection.py
# Test MCP server locally
python tests/test_local_mcp.py
# Test ChatGPT integration
python tests/test_chatgpt_integration.py
โ๏ธ Configuration
The server is pre-configured with:
- Database: biopref (localhost:5432)
- User: ginugeorge
- Schema: public
- Connection Timeout: 10 seconds
- Query Timeout: 30 seconds
No environment variables or additional configuration needed!
๐ง Database Schema
Products Table
id- UUID product identifiername- Product name (e.g., "Biodegradable Soap")
Categories Table
id- UUID category identifiername- Category name (e.g., "Cleaning Agents")
Additional Tables
category_product_map- Links products to categoriesacquisition- Contract values and funding agenciesawards- Award informationcontract_bio_entry- Contract bio entries
๐ฌ Example Claude Conversations
- "Find all soap products in the Bio Preferred database"
- "What categories are available?"
- "Show me the structure of the products table"
- "How many products are in each category?"
๐จ Troubleshooting
Common Issues
-
"Database connection failed"
- Ensure PostgreSQL is running:
psql -l - Check the
bioprefdatabase exists
- Ensure PostgreSQL is running:
-
"MCP server not found"
- Verify the Python path in Claude Desktop configuration
- Test locally:
python tests/test_local_mcp.py
-
"No tools available"
- Check server logs in Claude Desktop
- Run tests to verify functionality
Debug Commands
# Test database connection
python tests/test_database_connection.py
# Test MCP server
python tests/test_local_mcp.py
# Check server status
ps aux | grep python
๐ Documentation
- Claude Desktop Setup - Complete setup guide
- Configuration Details - Configuration reference
- Testing Guide - Comprehensive testing instructions
- Integration Guide - ChatGPT integration details
๐ฏ Status
โ Production Ready - All tests passing, optimized for Claude Desktop
Your Bio Preferred MCP server is ready to provide AI agents with access to real product data! ๐
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.