Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

mcp-sqlite-bun-server

MCP.Pizza Chef: jacksteamdev

The mcp-sqlite-bun-server is a Model Context Protocol (MCP) server that integrates SQLite database capabilities into AI workflows. It allows models to run SQL queries directly on business data, perform data analysis, and automatically generate business insight memos. This server is designed to enhance AI applications with structured data querying and business intelligence, facilitating real-time, data-driven decision-making. Installation requires Bun runtime, and setup integrates seamlessly with Claude Desktop, making it accessible for developers building AI copilots and agents that need database interaction and business analytics.

Use This MCP server To

Run SQL queries on business databases in AI workflows Generate automated business insight memos from data Analyze structured business data for decision support Integrate SQLite querying into AI copilots and agents Enable real-time data-driven reasoning in AI models

README

SQLite MCP Server

Overview

A Model Context Protocol (MCP) server implementation that provides database interaction and business intelligence capabilities through SQLite. This server enables running SQL queries, analyzing business data, and automatically generating business insight memos.

SQLite Server MCP server

Installation

  1. Install Bun if you haven't already
  2. Clone this repository
  3. Install dependencies:
    bun install
  4. Run the setup script to configure the server in Claude Desktop:
    bun run setup

The setup script will automatically add the server configuration to your Claude Desktop config file, located at:

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

Components

Resources

The server exposes a single dynamic resource:

  • memo://insights: A continuously updated business insights memo that aggregates discovered insights during analysis
    • Auto-updates as new insights are discovered via the append-insight tool

Prompts

The server provides a demonstration prompt:

  • mcp-demo: Interactive prompt that guides users through database operations
    • Required argument: topic - The business domain to analyze
    • Generates appropriate database schemas and sample data
    • Guides users through analysis and insight generation
    • Integrates with the business insights memo

Tools

The server offers six core tools:

Query Tools
  • read-query

    • Execute SELECT queries to read data from the database
    • Input:
      • query (string): The SELECT SQL query to execute
    • Returns: Query results as array of objects
  • write-query

    • Execute INSERT, UPDATE, or DELETE queries
    • Input:
      • query (string): The SQL modification query
    • Returns: { affected_rows: number }
  • create-table

    • Create new tables in the database
    • Input:
      • query (string): CREATE TABLE SQL statement
    • Returns: Confirmation of table creation
Schema Tools
  • list-tables

    • Get a list of all tables in the database
    • No input required
    • Returns: Array of table names
  • describe-table

    • View schema information for a specific table
    • Input:
      • table_name (string): Name of table to describe
    • Returns: Array of column definitions with names and types
Analysis Tools
  • append-insight
    • Add new business insights to the memo resource
    • Input:
      • insight (string): Business insight discovered from data analysis
    • Returns: Confirmation of insight addition
    • Triggers update of memo://insights resource

Development

Project Structure

  • src/index.ts: Main server implementation
  • src/logger.ts: Logging utility
  • scripts/setup.ts: Claude Desktop configuration script

Logging

The server maintains detailed logs in:

  • server.log: Located in the project root directory
  • Logs include timestamps, log levels (DEBUG, INFO, WARN, ERROR, FATAL), and structured metadata

Database

The SQLite database file is created at:

  • data.sqlite: Located in the project root directory
  • Created automatically if it doesn't exist

Available Scripts

  • bun run setup: Configure the server in Claude Desktop
  • bun run lint: Run ESLint checks
  • bun run lint:fix: Fix ESLint issues automatically
  • bun run inspect: Run the MCP inspector

License

This MCP server is licensed under the MIT License. See the LICENSE file for details.

mcp-sqlite-bun-server FAQ

How do I install the mcp-sqlite-bun-server?
Install Bun runtime, clone the repository, run 'bun install' to install dependencies, then run 'bun run setup' to configure the server in Claude Desktop.
What operating systems does the setup support?
The setup script is designed for macOS, configuring Claude Desktop at '~/Library/Application Support/Claude/claude_desktop_config.json'.
Can this server generate business insights automatically?
Yes, it can analyze data and generate automated business insight memos to assist decision-making.
Is the server limited to SQLite databases?
Yes, this MCP server specifically provides interaction with SQLite databases for structured data querying.
How does this server integrate with AI models?
It exposes SQLite database querying as a resource, allowing AI models to run SQL queries and retrieve structured data in real time.
What LLM providers can work with this MCP server?
It is compatible with models from OpenAI, Anthropic Claude, and Google Gemini, among others supporting MCP.
Does the server support dynamic resource exposure?
Yes, it exposes a dynamic resource that enables flexible querying and data interaction.
Can I use this server for business intelligence applications?
Absolutely, it is designed to facilitate business intelligence by enabling SQL queries and automated insight generation.