SQLite MCP Server
Provides read and write access to multiple SQLite databases through the Model Context Protocol, with safety features like parameterized queries and required WHERE clauses for destructive operations.
README
SQLite MCP Server
A general-purpose Model Context Protocol (MCP) server for SQLite databases. This server provides read and write access to any SQLite database in the database folder through Claude Desktop and other MCP clients.
Features
- Multi-Database Support: Work with multiple SQLite databases in a single server
- Read Operations: Query tables, list databases, describe schemas
- Write Operations: Insert, update, and delete data safely
- Safety Features: Parameterized queries, validation, and required WHERE clauses for destructive operations
Available Tools
Database Discovery
list_databases- List all available .db files in the database folderlist_tables- List all tables in a specific databasedescribe_table- Get detailed table structure (columns, types, constraints)
Read Operations
query_database- Execute SELECT queries with automatic LIMIT protection
Write Operations
insert_data- Insert new rows into tablesupdate_data- Update existing rows (requires WHERE clause)delete_data- Delete rows (requires WHERE clause)execute_raw_sql- Execute any SQL query (use with caution)
Installation
Prerequisites
- Python 3.10 or higher
- pip (Python package manager)
Setup
-
Clone or download this repository
-
Install dependencies:
pip install -r requirements.txt
- Add your databases:
- Place your SQLite
.dbfiles in thedatabase/folder - The server will work with any
.dbfile you add to this folder - You can add multiple databases and switch between them
- Place your SQLite
Usage
Running Locally
Test the server locally:
python sqlite_mcp.py
Claude Desktop Integration
Add the server to your Claude Desktop configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Option A: Using Python directly
{
"mcpServers": {
"sqlite-mcp-server": {
"command": "python",
"args": [
"C:/Users/YOUR_USERNAME/path/to/sqlite-mcp-server/sqlite_mcp.py"
]
}
}
}
Option B: Using uv with fastmcp
{
"mcpServers": {
"sqlite-mcp-server": {
"command": "uv",
"args": [
"run",
"--with", "fastmcp",
"fastmcp", "run",
"C:/Users/YOUR_USERNAME/path/to/sqlite-mcp-server/sqlite_mcp.py"
]
}
}
}
Replace C:/Users/YOUR_USERNAME/path/to/sqlite-mcp-server/ with your actual project path.
Restart Claude Desktop
After updating the configuration:
- Completely quit Claude Desktop
- Restart the application
- The SQLite MCP Server should now be available
Example Usage in Claude
Once connected, you can interact with your databases through Claude:
"List all available databases"
"Show me the tables in ecommerce.db"
"Describe the structure of the users table in ecommerce.db"
"Query the top 10 products from the products table in ecommerce.db"
"Insert a new user with name 'John Doe' and email 'john@example.com' into ecommerce.db"
Security Notes
- The server uses parameterized queries to prevent SQL injection
- Write operations require explicit WHERE clauses to prevent accidental mass updates/deletes
- Query results are limited to 1000 rows by default
Project Structure
sqlite-mcp-server/
├── sqlite_mcp.py # Main MCP server
├── database/ # SQLite database files go here
│ └── *.db # Your database files
├── requirements.txt # Python dependencies
├── .gitignore # Git ignore rules
└── README.md
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.