Cursor IDE

Overview

Cursor is an AI-first code editor that enhances your development workflow with intelligent code completion and chat capabilities. With Lemonado's MCP integration, you can query your business data directly from Cursor's AI assistant.

Prerequisites

• Cursor IDE installed (version 0.42.0 or later)
• Active Lemonado AI Connector with MCP endpoint
• macOS, Windows, or Linux system

Setup Instructions

Step 1: Locate Cursor Configuration

Cursor stores MCP configuration in a JSON file. The location depends on your operating system:

• macOS: ~/Library/Application Support/Cursor/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
• Windows: %APPDATA%\Cursor\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
• Linux: ~/.config/Cursor/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

Step 2: Configure MCP Settings

Edit the MCP settings file to add Lemonado:

{
  "mcpServers": {
    "lemonado": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetch",
        "https://mcp.lemonado.io/mcp"
      ],
      "env": {
        "MCP_AUTH_TYPE": "oauth",
        "MCP_OAUTH_PROVIDER": "lemonado"
      }
    }
  }
}

Step 3: Authenticate with OAuth

When you first use the Lemonado connector, you'll be prompted to authenticate via OAuth. This will open a browser window where you can log in to your Lemonado account and select which AI Connector to use.

Step 4: Restart Cursor

1. Completely quit Cursor (Cmd+Q on macOS, Alt+F4 on Windows)
2. Reopen Cursor
3. The MCP connection will be automatically established

Step 5: Test the Connection

In Cursor's AI chat (Cmd+K or Ctrl+K), try a query like:

@lemonado What data sources are available?

If configured correctly, you'll receive a list of your connected data sources.

Using Lemonado in Cursor

Basic Queries

Use the @lemonado mention to query your data:

@lemonado Show me revenue trends for Q4 2024

@lemonado List all customers who signed up last month

Code Generation with Real Data

Cursor can generate code based on your actual data structure:

@lemonado Generate a TypeScript interface for our customer data model

@lemonado Create a SQL query to find top performing products

Data Analysis

@lemonado Analyze the correlation between marketing spend and conversions

@lemonado What's the average customer lifetime value by segment?

Advanced Configuration

Multiple AI Connectors

You can add multiple instances of Lemonado, each will prompt for OAuth authentication:

{
  "mcpServers": {
    "lemonado-sales": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetch",
        "https://mcp.lemonado.io/mcp"
      ],
      "env": {
        "MCP_AUTH_TYPE": "oauth",
        "MCP_OAUTH_PROVIDER": "lemonado"
      }
    },
    "lemonado-analytics": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetch",
        "https://mcp.lemonado.io/mcp"
      ],
      "env": {
        "MCP_AUTH_TYPE": "oauth",
        "MCP_OAUTH_PROVIDER": "lemonado"
      }
    }
  }
}

Features & Capabilities

Supported Operations

• Read Operations: Query any connected database or SaaS tool
• Data Analysis: Perform aggregations and calculations
• Schema Inspection: View table structures and relationships
• Real-time Data: Access the latest synchronized data

Context Awareness

Cursor's AI understands your project context and can:

• Suggest queries based on your code
• Generate type-safe interfaces from your data
• Create API endpoints that match your data structure
• Write tests using real data examples

Query Assistance

With Lemonado connected, Cursor can:

• Suggest appropriate queries for your use case
• Generate documentation from your data schema
• Help you understand your data structure

Best Practices

1. Use Specific Queries

Instead of broad queries, be specific:

• ❌ "Show me all data"
• ✅ "Show me customer orders from last week with totals over $1000"

2. Leverage Context

Reference your code when asking questions:

@lemonado Based on this UserService class, what customer fields should I include?

3. Iterate on Results

Start simple and refine:

1. Get basic data structure
2. Add filters and conditions
3. Optimize the query

4. Security Considerations

• OAuth tokens are managed securely by the MCP client
• Authentication happens in your browser
• You control which AI Connector to use
• Monitor usage in your Lemonado dashboard

Troubleshooting

Connection Not Working

1. Check MCP settings file location

   • Ensure the file is in the correct directory
   • Verify JSON syntax is valid

2. OAuth authentication issues

   • Clear browser cookies and try again
   • Ensure you're logged into the correct Lemonado account

3. Check Cursor version

   • Update to the latest version if needed
   • Some older versions may have MCP bugs

No Response from Lemonado

• Verify your AI Connector is active in Lemonado
• Check if you've exceeded rate limits
• Ensure your data sources are properly connected

Slow Queries

• Optimize your Lemonado connector permissions
• Use specific filters in your queries
• Consider upgrading your Lemonado plan for better performance

Authentication Errors

• Re-authenticate via OAuth if prompted
• Check if your AI Connector has been disabled
• Ensure you selected the correct AI Connector during OAuth flow

Tips & Tricks

Quick Data Exploration

@lemonado Show me the schema for the customers table

Generate Mock Data

@lemonado Create 5 sample customer records based on our actual schema

Debug Queries

@lemonado Explain the performance implications of this SQL query

Data Validation

@lemonado Check if there are any null values in critical fields

Comparison: Cursor vs Other IDEs

Next Steps

• Explore available data connectors
• Learn about query optimization