SQLite MCP Server
About
A lightweight Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to autonomously interact with SQLite databases.
Details
- Author
- dubydu
- Downloads
- 243
- Categories
- Database
Jump to
- Enables LLMs to autonomously read and write SQLite databases
- Lightweight MCP server implementation
- Supports custom database file paths via --db-path
- Works with MCP clients like 5ire and Claude Desktop
- Requires Python 3.12.7+, MCP 1.6.0+, and PyTest
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
SQLite MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, set up a Python virtual environment, install dependencies with pip install -r requirements.txt, then run python src/entry.py --db-path /path/to/your/database.db. Configure your MCP client (e.g., 5ire or Claude Desktop) with the appropriate command and arguments.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"sqlite mcp server": {
"sqlite-mcp": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}
}McpServers
{
"sqlite-mcp": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}SQLite MCP Server
A lightweight Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to autonomously interact with SQLite databases.
Showcases
<video src="https://github.com/user-attachments/assets/b4c43fc1-02de-435a-9a9b-1c193ce6baec" autoplay loop muted></video>
Installation
1. Clone the repository:
git clone https://github.com/dubydu/sqlite-mcp.git
cd sqlite-mcp
2. Set up a virtual environment (recommended):
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
3. Install dependencies:
pip install -r requirements.txt
Usage
Basic Start
python src/entry.py --db-path /path/to/your/database.db
Command Line Options
- --db-path: Path to SQLite database file (default: "./db/database.db")
Available MCP Tools
For the full list of tools, see the MCP_TOOLS.md
MCP CLients Configuration
- 5ire
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
