Local Database Analytics MCP Server

A Python-based Model Context Protocol (MCP) server that exposes a local SQLite e-commerce database to AI assistants like Claude. Built with FastMCP, SQLAlchemy, and Pandas.

What is MCP? The Model Context Protocol (by Anthropic) lets AI models securely interact with local tools and data. This server teaches Claude about your database so it can query, analyze, and explain the data — all using natural language.

---

Features

Tools (11 total)

Tool	Description
list_tables	List all tables in the database
describe_table	Show schema/columns of a specific table
get_sample_rows	Return N sample rows from a table
get_row_count	Count rows with optional WHERE filter
run_sql_query	Execute any safe SELECT query
summarize_column	Stats: min/max/mean/nulls/unique for any column
find_top_n	Top N rows sorted by a column
group_and_aggregate	GROUP BY + SUM/AVG/COUNT/MIN/MAX
detect_nulls	Find columns with missing data
compute_correlation	Pearson correlation between two columns
time_series_summary	Aggregate data by day/week/month

Resources

URI	Description
db://schema	Full database schema
db://tables/{name}	Schema for a specific table

Prompts

• analyze_table — Full statistical analysis of any table
• business_summary — Executive-level e-commerce report
• find_anomalies — Data quality & outlier detection

---

Database Schema

customers ──< orders ──< order_items >── products

• customers: 15 records with name, email, city, signup date
• products: 15 products across Electronics, Books, Sports, Home, Stationery
• orders: 60 orders with status (completed/pending/cancelled) and totals
• order_items: Line items linking orders to products

---

Project Structure

MCP_Server/
├── server.py               # FastMCP server entry point
├── requirements.txt        # Python dependencies
├── database/
│   ├── engine.py           # SQLAlchemy DB connection
│   └── seed_data.py        # Seed script (creates + populates DB)
├── tools/
│   ├── query.py            # Core SQL tools (Phase 2)
│   └── analytics.py        # Analytics tools (Phase 3)
├── resources/
│   └── schema.py           # DB schema as MCP resources
├── prompts/
│   └── templates.py        # Pre-built analyst prompts
├── tests/
│   └── test_tools.py       # Unit tests
└── data/
    └── analytics.db        # SQLite database (auto-created)

---

Getting Started

1. Clone the repo

git clone https://github.com/manohar135/Local-Database-Analytics-MCP-Server.git
cd Local-Database-Analytics-MCP-Server

2. Create a virtual environment and install dependencies

python -m venv .venv
source .venv/bin/activate       # On Windows: .venv\Scripts\activate
pip install -r requirements.txt

3. Seed the database

python database/seed_data.py

4. Launch the MCP Inspector (dev mode)

fastmcp dev server.py

5. Run tests

pytest tests/ -v

---

Tech Stack

Technology	Role
FastMCP	MCP server framework
SQLite	Zero-config local database
SQLAlchemy	DB engine & ORM
Pandas	Analytics & aggregation
Pydantic	Input validation
Pytest	Unit testing

---

Example Claude Conversations

Once connected to Claude Desktop, try:

• "What tables do you have access to?"
• "Give me a business summary of the sales data"
• "Which products are selling the most?"
• "Are there any data quality issues in the orders table?"
• "Show me monthly revenue trends for the past year"