Skip to main content

Developer Tools Overview

About this Document

Learn about the five core tools provided by Rabetbase and how they work together to boost development efficiency by more than 10 times.

Rabetbase Five-Tool Suite

Five-Tool Suite Overview​

Rabetbase provides developers with a complete toolchain:

ToolOne-Line PositioningCore Value
OpenAPIStandard HTTP InterfaceCross-language calls, third-party system integration, no SDK dependency
CLIProject Lifecycle ManagementCreate projects, generate configurations, sync menus, build and deploy
TypeScript SDKFrontend Data AccessType safety, unified error handling, efficient queries
Java SDKBackend Data AccessServer-side complex business logic development
MCP ServerAI Business Intelligence EngineLet AI understand your business data and generate accurate code

Core Advantage: The five tools are deeply integrated, covering the complete scenario from interface calls to AI-assisted development.

OpenAPI: Standard HTTP Interface​

# Call directly via HTTP without installing SDK
curl -X POST https://api.lovrabet.com/openapi/v1/data/filter \
  -H "Authorization: Bearer YOUR_ACCESS_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelCode": "customers", "pageSize": 10}'

What does OpenAPI do for you?

  • Cross-language calls, usable by Python, Go, PHP, etc.
  • Third-party system integration without depending on specific SDKs
  • RESTful style, standard HTTP protocol
  • Complete authentication mechanism with AccessKey or Token modes

CLI: Project Lifecycle Management​

# Install
npm install -g @lovrabet/cli

# Common commands
lovrabet auth          # Login authentication
lovrabet create        # Create project
lovrabet start         # Start development server
lovrabet api pull      # Pull dataset configuration, generate SDK code
lovrabet menu sync     # Sync menu to workbench
lovrabet build         # Build production version

What does CLI do for you?

  • One-click project structure creation, no configuration from scratch
  • Auto-generate SDK configuration, no manual type definitions
  • Sync menus to workbench, no manual backend login required
  • Built-in proxy in development server, no CORS issues to handle

TypeScript SDK: Frontend Data Access​

import { lovrabetClient } from '@/api/client';

// List query (with filtering, pagination)
const result = await lovrabetClient.models.customers.filter({
  where: { status: { $eq: 'active' } },
  select: ['id', 'name', 'phone'],
  orderBy: [{ createTime: 'desc' }],
  pageSize: 20,
});

// Single record query
const customer = await lovrabetClient.models.customers.getOne(customerId);

// Create data
await lovrabetClient.models.customers.create({
  name: 'Zhang San',
  phone: '13800138000',
});

// Custom SQL (complex report scenarios)
const stats = await lovrabetClient.api.executeSql('sql-code-xxx', {
  startDate: '2024-01-01',
  endDate: '2024-12-31',
});

What does TypeScript SDK do for you?

  • Type safety with IDE intelligent hints
  • Unified error handling, no try-catch everywhere
  • Auto-handle authentication, browser auto-uses Cookie
  • Built-in pagination, filtering, sorting, no manual parameter concatenation

Java SDK: Backend Data Access​

// Initialize client
LovrabetClient client = new LovrabetClient(accessKey, secretKey);

// List query
FilterResult<Customer> result = client.models("customers")
    .filter(new FilterParams()
        .where("status", "active")
        .select("id", "name", "phone")
        .orderBy("createTime", "desc")
        .pageSize(20));

// Single record query
Customer customer = client.models("customers").getOne(customerId);

// Create data
client.models("customers").create(new Customer("Zhang San", "13800138000"));

What does Java SDK do for you?

  • Server-side secure calls, keys not exposed to frontend
  • Complex business logic handling like batch operations, transaction management
  • Seamless integration with existing Java ecosystem
  • Suitable for scheduled tasks, background services, etc.

MCP: AI's Business Intelligence Brain​

Why is MCP Critical?

Traditional AI can only "read documentation" and knows field names but doesn't understand business relationships.

MCP lets AI "understand business" - it knows table relationships, field business meanings, and data flow rules.

Configure MCP​

Configure in Claude Desktop or Cursor:

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

What can MCP do?​

After configuration, you can chat directly with AI:

You: List all datasets
AI: (Calls MCP) Your application has 8 datasets...

You: View customer table fields
AI: (Calls MCP) The customer table has the following fields: id, name, phone...

You: Help me write a customer list page
AI: (Understands data structure via MCP) OK, I'll generate the code...

Efficiency Comparison​

ScenarioTraditional AI DevelopmentUsing MCP
Data Exploration20-30 minutes (checking docs, testing APIs)< 5 seconds
SQL Design30-60 minutes (iterative debugging)< 2 minutes
Code Generation20-30 minutes (multiple corrections)5 minutes
Complete Page2-3 hours10-15 minutes

Code Accuracy:

  • Traditional AI: 60-70% (requires multiple iterations)
  • Using MCP: 95%+ (basically works on first try)

Five-Tool Suite Collaborative Workflow​

┌─────────────────────────────────────────────────────────────────┐
│                        Before Development                        │
│  1. lovrabet create     → Create project                        │
│  2. lovrabet api pull   → Generate SDK configuration            │
│  3. Configure MCP       → Let AI understand your data           │
├─────────────────────────────────────────────────────────────────┤
│                        During Development                        │
│  4. AI + MCP            → Explore data, generate code           │
│  5. SDK calls           → Type-safe data operations             │
│  6. lovrabet start      → Real-time preview and debugging       │
├─────────────────────────────────────────────────────────────────┤
│                        After Development                         │
│  7. lovrabet build      → Build production version              │
│  8. lovrabet menu sync  → Sync menu to workbench                │
└─────────────────────────────────────────────────────────────────┘

Real-world Case: User List Page​

Requirement: Display user list including basic info + membership tags + last login time (requires joining 3 tables)

Traditional Way​

  1. Check docs to find field names → guess wrong → check again
  2. Write SQL → JOIN method wrong → modify again
  3. Write code → field name typo → debug again
  4. Repeat 4-5 rounds → Takes 2-3 hours

Using MCP​

You: I need a user list page showing user basic info, membership tags, and last login time

AI: (Analyzes via MCP)
- user_info table: basic info
- user_membership table: membership info
- user_login_log table: login records
Let me help you write a join query...

(Generates complete code with 100% accurate field names)

Time: 10 minutes

Next Steps​