SQLite MCP Server

by javsanmar5

7 stars
155 downloads
Not rated
GitHub

About

Implementation of an MCP (Model Context Protocol) Server for SQLite. It provides an AI model with context and the ability to execute SQL queries.

Details

Author
javsanmar5
GitHub stars
7
Downloads
155
Categories
Database

- list_tables – lists all tables in the SQLite database
- read_query – executes SELECT queries on the database
- Runs as a Docker container for easy deployment
- Integrates with MCP‑compatible AI clients like Claude Desktop

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:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name SQLite MCP Server
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Clone the repository, build the Docker image (docker build -t mcp/sqlite .), then add the provided JSON configuration to your AI client’s configuration file, specifying --db-path (e.g., test_db.sqlite3). After restarting the client, the tools list_tables and read_query become available.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "sqlite mcp server": {
            "mcp-server.sqlite": {
                "command": "docker",
                "args": [
                    "build",
                    "-t",
                    "mcp/sqlite",
                    "."
                ]
            }
        }
    }
}

McpServers

{
    "mcp-server.sqlite": {
        "command": "docker",
        "args": [
            "build",
            "-t",
            "mcp/sqlite",
            "."
        ]
    }
}

SQLite MCP Server

A Model Context Protocol (MCP) server implementation using TypeScript for interacting with an SQLite database. This server provides an interactive interface for executing SQL queries, managing database schemas, and synthesizing business insights—all within an extensible protocol framework.

Not familiar with MCP? Check out the What is an MCP? section below.

Features

| Command | Description | Example |
|---------|-------------|---------|
| list_tables | List all tables on the SQLite database | - |
| read_query | Execute SELECT queries on the SQLite database | SELECT * FROM users WHERE age > 18 |

Installation & Setup

git clone https://github.com/javsanmar5/mcp-server.sqlite.git
cd mcp-server.sqlite

Since this hasn't been published as an npm package yet, we'll focus on the Docker installation method:

1. Build the Docker image

docker build -t mcp/sqlite .

2. Configure your AI client

Add the following to your AI client's configuration file:

"mcpServers": {
  "sqlite": {
    "command": "docker",
    "args": [
      "run",
      "--rm",
      "-i",
      "-v",
      "mcp-test:/mcp",
      "mcp/sqlite",
      "--db-path",
      "test_db.sqlite3"
    ]
  }
}

If you don't know what is that json file you might want to see the Client Configuration Guide.

3. Restart your AI client

After restarting, the MCP Tools should be available in your AI client's interface.
_On Windows, you may need to manually kill the process for the changes to take effect._

Documentation

What's an MCP?

Model Context Protocol (MCP) is a standardized way for AI models to interact with external tools and services. It allows AI assistants to perform actions like running database queries, accessing external APIs, or manipulating files through a defined protocol interface.

MCPs extend AI capabilities beyond conversation by providing structured access to tools and data sources without requiring direct integration into the AI model itself.

Tutorial: Setting up with Claude Desktop

Claude Desktop is one of many AI clients that support MCP servers. Here's how to set it up on Windows:

1. Press Windows Key + R to open the Run dialog
2. Type %appdata%\Claude and press Enter
3. Create a new file called claude_desktop_config.json if it doesn't exist already
4. Add the configuration from step 2 of the setup instructions above
5. Save the file and restart Claude Desktop
6. You should now see the SQLite tools available in your Claude interface

License

This project is licensed under the MIT License.

Contributing

This project was created primarily for learning purposes. However, if you'd like to contribute, feel free to submit a Pull Request and I'll review it.

Thanks for your interest!

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.