AI - Model Context Protocol (MCP)

The Model Context Protocol (MCP) is a standard for connecting various data sources (like your SQLite Cloud database) to Large Language Models (LLMs). The MCP Server for SQLite Cloud provides tools for executing queries, managing schemas, and analyzing query performance.

Features

Query Execution: Perform SELECT, INSERT, UPDATE, and DELETE SQL operations on SQLite Cloud databases.
Schema Management: Create tables, list existing ones, and retrieve schema details.
Command Execution: Run predefined commands supported by SQLite Cloud.
Performance Analysis: Identify slow queries, analyze query plans, and reset query statistics.

Explore the available tools here.

Getting Started

To use the MCP Server, create a free account on SQLite Cloud and obtain your Connection String.

Requirements

You need Node.js installed on your computer to run the MCP Server. To check if Node.js is installed, open a terminal:

Linux: Open the terminal from the Applications menu.
macOS: Open the Terminal app from the Applications folder or use Spotlight Search (Cmd+Space) and type “Terminal.”
Windows: Press Win + R, type cmd, and press Enter to open the Command Prompt. Alternatively, search for “Command Prompt” in the Start menu.

Then type the following command and press Enter:

node --version

If the command returns a version number, Node.js is installed. If you see an error like “command not found” or “node is not recognized,” download and install Node.js from nodejs.org.

Configure the AI Agent

This guide explains how to connect the MCP Server for SQLite Cloud to common AI agents that support MCP.
Find a list of supported tools and IDEs here.

After configuring your AI agent, try asking it questions about your SQLite Cloud database, such as:

What’s in my database on SQLite Cloud?”
“What are the three most popular tracks by revenue in my SQLite Cloud database?

Explore or manipulate your database using natural language queries.

Claude Desktop

Refer to the official documentation for detailed instructions.

Open Claude Desktop and navigate to Settings.
Go to the Developer section and click on Edit Config to open the configuration file.

Add the following configuration:

{
  "mcpServers": {
    "sqlitecloud-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@sqlitecloud/mcp-server",
        "--connectionString",
        "<CONNECTION_STRING>"
      ]
    }
  }
}

Replace <CONNECTION_STRING> with your Connection String.

Save the configuration file and restart Claude Desktop.
You should see a Hammer icon in the bottom-right corner of the input box. Click the icon to view the list of discovered tools.

Cursor

Refer to the official documentation for detailed instructions.

In the root of your project, create the file .cursor/mcp.json.

Add the following configuration:

{
  "mcpServers": {
    "sqlitecloud-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@sqlitecloud/mcp-server",
        "--connectionString",
        "<CONNECTION_STRING>"
      ]
    }
  }
}

Replace <CONNECTION_STRING> with your Connection String.

Save the mcp.json file.
Open the Settings page and navigate to the MCP section. You should see the MCP server with a green status indicator.
In the Chat panel, select the “Agent” mode to interact with the AI model using the MCP Server.

VSCode Copilot

Refer to the official documentation for detailed instructions.

In the root of your project, create the file .vscode/mcp.json.

Add the following configuration:

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "sqlitecloud-connection-string",
        "description": "Set the SQLite Cloud Connection String",
        "password": true
      }
    ],
    "servers": {
      "sqlitecloud-mcp-server": {
        "type": "stdio",
        "command": "npx",
        "args": [
          "-y",
          "@sqlitecloud/mcp-server",
          "--connectionString",
          "${input:sqlitecloud-connection-string}"
        ]
      }
    }
  }
}

Save the mcp.json file.
Open Copilot Chat and select the Agent mode from the menu near the Send button. A tool icon will appear, showing the discovered tools. Before starting the server, VSCode will prompt you to enter your Connection String.