Skip to main content
Glama
bke1302

Business MCP Server

by bke1302

πŸ”Œ Business MCP Server

An MCP (Model Context Protocol) server that connects Claude β€” or any MCP-compatible AI client β€” to a real business database. It lets the AI query customers, orders, and revenue using natural language, by exposing safe, well-defined tools over the database.

Built as a hands-on demonstration of Python, APIs, and the Model Context Protocol β€” the emerging standard for connecting LLMs to real-world systems.


🧠 What is MCP?

Large Language Models only know what they were trained on β€” they can't read your database, CRM, or spreadsheet. MCP is an open standard (introduced by Anthropic) that acts like a universal adapter between an AI model and external systems.

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”      β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”      β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚ Claude  β”‚ ───► β”‚  MCP Server  β”‚ ───► β”‚  SQLite (DB)   β”‚
β”‚ (client)β”‚ ◄─── β”‚  (this repo) β”‚ ◄─── β”‚  customers,    β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜      β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜      β”‚  orders        β”‚
                                       β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

The MCP server exposes tools (actions). The AI decides when and how to call them β€” you simply grant the capability.


Related MCP server: Database MCP Server

πŸ› οΈ Tools exposed

Tool

Description

list_customers()

Returns all customers (name, email, city, join date).

search_customers(keyword)

Finds customers by name or city.

get_customer_orders(customer_id)

Returns all orders for a given customer.

revenue_summary()

Total revenue from completed orders + order counts.

All database access goes through a single helper that uses parameterized queries (? placeholders) to prevent SQL injection.


πŸ“¦ Tech stack

  • Python 3.13

  • MCP Python SDK (mcp[cli]) β€” FastMCP

  • SQLite (standard library sqlite3) β€” the business database


πŸš€ Getting started

# 1. Clone and enter the project
git clone https://github.com/bke1302/business-mcp-server.git
cd business-mcp-server

# 2. Create and activate a virtual environment
python -m venv venv
venv\Scripts\activate        # Windows
# source venv/bin/activate   # macOS / Linux

# 3. Install dependencies
pip install -r requirements.txt

# 4. Create the sample database
python init_db.py

Connect to Claude Code

claude mcp add business-db -- python /full/path/to/server.py

Then ask Claude naturally:

"How much revenue have we made?" "Show me Maya's orders." "Which customers are from Tel Aviv?"

Claude will call the right tool and answer from your live data.


πŸ“ Project structure

business-mcp-server/
β”œβ”€β”€ server.py          # The MCP server β€” defines and serves the tools
β”œβ”€β”€ init_db.py         # Creates and seeds the SQLite database
β”œβ”€β”€ requirements.txt   # Python dependencies
β”œβ”€β”€ .gitignore
└── README.md

πŸ“š What this project demonstrates

  • Building an MCP server from scratch with the official Python SDK

  • Designing clear, well-documented tools an AI can reason about

  • Safe database access with parameterized SQL queries

  • Clean, portable code (absolute paths, isolated virtual environment)


πŸ—ΊοΈ Roadmap

  • Add Google Sheets as an alternative data source

  • Add write tools (create / update orders)

  • Add automated tests


Built while transitioning from operations management into AI engineering β€” closing the gap from low-code automation to real Python & technical architecture.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    A
    maintenance
    Allows AI assistants to list tables, read data, and execute SQL queries through a controlled interface, making database exploration and analysis safer and more structured.
    3
    11,624 PyPI
    1,389
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to securely interact with multiple databases (MySQL, PostgreSQL) via natural language queries, with cross-database querying and enterprise-grade security.
    8 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI agents to interact with PostgreSQL or MySQL databases using natural language. Supports SQL queries, schema discovery, and pre-built aggregations without writing SQL.
    191 npm
    MIT
  • A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI assistants to query business databases directly via natural language, with enforced read-only access and secure query limits. Supports SQLite and PostgreSQL, and works with any OpenAI-compatible model.
    0
    ISC