Quick Start

Complete Lovrabet MCP configuration in 3 minutes, enabling AI editors to understand your business data.

1. Configure MCP Server

Add MCP configuration to your AI editor.

Using npx (Recommended)

No installation required, use directly:

{
  "mcpServers": {
    "lovrabet-dataset": {
      "command": "npx",
      "args": ["-y", "@lovrabet/dataset-mcp-server"],
      "env": {
        "LOVRABET_APP_CODE": "your-app-code"
      }
    }
  }
}

Global Installation

If you want to install globally:

npm install -g @lovrabet/dataset-mcp-server

Then configure:

{
  "mcpServers": {
    "lovrabet-dataset": {
      "command": "lovrabet-dataset-mcp",
      "env": {
        "LOVRABET_APP_CODE": "your-app-code"
      }
    }
  }
}

Configuration File Location

Editor	Configuration File Path
Claude Desktop (Mac)	~/Library/Application Support/Claude/claude_desktop_config.json
Claude Desktop (Win)	%APPDATA%\Claude\claude_desktop_config.json
Cursor	Settings → MCP → Add Server
Claude Code	~/.claude/settings.json

2. Login Authentication

For first-time use, enter in your AI editor:

Please help me login to Lovrabet

AI will call the login tool and return a login link. Open it in your browser to complete login, and the cookie will be saved automatically.

tip

Login status is persisted, no need to login every time.

3. Start Using

After successful login, you can talk to AI like this:

Understanding Data Structure

List all datasets

View detailed information of the customer dataset

What are the required fields in the customer table?

Generating Code

Generate SDK code for the create operation of the order dataset

Help me write code to query all orders with status "completed"

Querying SQL

List all SQL queries

Search for sales-related SQL

Verify Configuration

After configuration is complete, enter in your AI editor:

List all datasets

If it returns a dataset list, the configuration is successful.

---

Next → Tool Reference | Use Cases