generateDataModel

Create statistical models from sample documents or text descriptions to generate realistic data for MongoDB-compatible databases without actual storage.

Instructions

Create a statistical model from sample documents or a text description for data generation

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Name for the model
`description`	No	Natural language description of the data structure
`samples`	No	Sample documents to train the model

Implementation Reference

src/mcp/mcp-server.js:895-926 (handler)

The core handler function that implements the generateDataModel tool logic. It processes input arguments to either infer a JSON schema from sample data or generate one from a description, persists the model using storage, caches it in memory, and returns a success response with model properties.

async generateDataModel(args) {
    const { name, description, samples } = args;
    
    if (samples && samples.length > 0) {
        const model = this.inferrer.inferSchema(samples);
        model.title = name;
        model.description = description || `DataFlood model: ${name}`;
        
        await this.storage.saveModel(config.storage.defaultDatabase, name, model);
        this.models.set(name, model);
        
        return {
            success: true,
            message: `Model '${name}' created from ${samples.length} samples`,
            properties: Object.keys(model.properties || {})
        };
    } else if (description) {
        const model = this.generateFromDescription(description);
        model.title = name;
        
        await this.storage.saveModel(config.storage.defaultDatabase, name, model);
        this.models.set(name, model);
        
        return {
            success: true,
            message: `Model '${name}' generated from description`,
            properties: Object.keys(model.properties || {})
        };
    } else {
        throw new Error('Either samples or description required');
    }
}

src/mcp/mcp-server.js:56-68 (schema)

The input schema and metadata definition for the generateDataModel tool, used for validation and advertised via tools/list endpoint.

{
    name: 'generateDataModel',
    description: 'Generate a DataFlood model from sample data or description',
    inputSchema: {
        type: 'object',
        properties: {
            name: { type: 'string', description: 'Name for the model' },
            description: { type: 'string', description: 'Natural language description of the data structure' },
            samples: { type: 'array', description: 'Sample documents to train the model', items: { type: 'object' } }
        },
        required: ['name']
    }
},

src/mcp/mcp-server.js:741-743 (registration)
Registration and dispatch point within the handleToolCall method's switch statement that routes tool calls named 'generateDataModel' to the handler function.
```
case 'generateDataModel':
    result = await this.generateDataModel(args);
    break;
```
src/mcp/mcp-server.js:1105-1108 (helper)
Supporting helper function called by the handler to generate a model schema from a natural language description using a prompt analyzer.
```
generateFromDescription(description) {
    const analysis = this.promptAnalyzer.analyze(description);
    return analysis.schema;
}
```

src/mcp/index.js:125-137 (schema)

Alternative input schema definition for generateDataModel in index.js tool definitions array.

{
  name: 'generateDataModel',
  description: 'Create a statistical model from sample documents or a text description for data generation',
  inputSchema: {
    type: 'object',
    properties: {
      name: { type: 'string', description: 'Name for the model' },
      description: { type: 'string', description: 'Natural language description of the data structure' },
      samples: { type: 'array', description: 'Sample documents to train the model', items: { type: 'object' } }
    },
    required: ['name']
  }
},

MongTap