Data Extractor

🚀 MCP Data Extractor Server Documentation

The MCP Data Extractor Server can extract strings and template literals from TypeScript or JavaScript source code and supports handling complex structures (such as arrays and objects). Here are the main features:

• Extract string values: Identify and extract string literals and template literals.
• Support for complex structures: Handle arrays and objects, including nested structures.
• Customizable extensions: Allow for supporting more AST node types by extending the extractStringValue and processValue methods.

🚀 Quick Start

✨ Features

• String Value Extraction: Recognize and extract string literals and template literals.
• Complex Structure Support: Handle arrays and objects, supporting nested structures.
• Custom Extension: Allow for supporting more AST node types by extending the extractStringValue and processValue methods.

💻 Usage Examples

Basic Usage

Input

export default {
  greeting: 'Hello, {{username}}!',
  message: `Welcome to ${appName}`
};

Output

{
  "greeting": "Hello, {{username}}!",
  "message": "Welcome to {{appName}}"
}

Advanced Usage

Input

export default {
  header: {
    title: '欢迎使用',
    description: `这是一个示例 ${description}`
  },
  list: ['项目1', '项目2', { id: '3' }]
};

Output

{
  "header.title": "欢迎使用",
  "header.description": "这是一个示例 {{description}}",
  "list.0": "项目1",
  "list.1": "项目2",
  "list.2.id": "3"
}

📚 Documentation

Adding New AST Node Types

To extend the supported node types, you can modify the extractStringValue method in src/index.ts:

private extractStringValue(node: t.Node): string | null {
  if (t.isStringLiteral(node)) {
    return node.value;
  } else if (t.isTemplateLiteral(node)) {
    return node.quasis.map(quasi => quasi.value.raw).join('{{}}');
  }
  // Add support for new node types
  if (t.isSome newNodeType(node)) {
    // Handle new node types
  }
  return null;
}

Custom Value Processing

By overriding the processValue method, you can extend the handling of other value types:

private processValue(value: t.Node, currentPath: string[]): void {
  if (t.isStringLiteral(value) || t.isTemplateLiteral(value)) {
    // Handle string values
  } else if (t.isArrayExpression(value)) {
    // Handle arrays
  } else if (t.isObjectExpression(value)) {
    // Handle objects
  }
  // Add handling for new value types
}

Custom AST Traversal

You can extend the AST traversal functionality by adding custom visitors:

traverse(ast, {
  ExportDefaultDeclaration(path: NodePath<t.ExportDefaultDeclaration>) {
    // Handle default exports
  },
  // Add new visitors
});

📦 Installation

Install Dependencies

npm install

Build the Server

npm run build

Development Mode (Automatic Rebuild)

npm run watch

Debugging Guide

Since the MCP server communicates via standard input and output, debugging can be challenging. We recommend using MCP Inspector for debugging:

npm run inspector

The Inspector provides a web interface to help you debug and analyze the code.

📄 License

This project is licensed under the MIT License. Please refer to the LICENSE file for detailed information.

With the above instructions, you can easily extend the functionality of the MCP Data Extractor Server and customize development according to your needs.