Skip to main content
Glama

mcp-data-extractor MCP Server

A Model Context Protocol server that extracts embedded data (such as i18n translations or key/value configurations) from TypeScript/JavaScript source code into structured JSON configuration files.

Features

  • Data Extraction:

    • Extracts string literals, template literals, and complex nested objects

    • Preserves template variables (e.g., Hello, {{name}}!)

    • Supports nested object structures and arrays

    • Maintains hierarchical key structure using dot notation

    • Handles both TypeScript and JavaScript files with JSX support

    • Replaces source file content with "MIGRATED TO " after successful extraction (configurable)

  • SVG Extraction:

    • Extracts SVG components from React/TypeScript/JavaScript files

    • Preserves SVG structure and attributes

    • Removes React-specific code and props

    • Creates individual .svg files named after their component

    • Replaces source file content with "MIGRATED TO " after successful extraction (configurable)

Related MCP server: Basic MCP Server

Usage

Add to your MCP Client configuration:

{
  "mcpServers": {
    "data-extractor": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-data-extractor"
      ],
      "disabled": false,
      "autoApprove": [
        "extract_data",
        "extract_svg"
      ]
    }
  }
}

Basic Usage

The server provides two tools:

1. Data Extraction

Use extract_data to extract data (like i18n translations) from source files:

<use_mcp_tool>
<server_name>data-extractor</server_name>
<tool_name>extract_data</tool_name>
<arguments>
{
  "sourcePath": "src/translations.ts",
  "targetPath": "src/translations.json"
}
</arguments>
</use_mcp_tool>

2. SVG Extraction

Use extract_svg to extract SVG components into individual files:

<use_mcp_tool>
<server_name>data-extractor</server_name>
<tool_name>extract_svg</tool_name>
<arguments>
{
  "sourcePath": "src/components/icons/InspectionIcon.tsx",
  "targetDir": "src/assets/icons"
}
</arguments>
</use_mcp_tool>

Source File Replacement

By default, after successful extraction, the server will replace the content of the source file with:

  • "MIGRATED TO " for data extraction

  • "MIGRATED TO " for SVG extraction

This helps track which files have already been processed and prevents duplicate extraction. It also makes it easy for LLMs and developers to see where the extracted data now lives when they encounter the source file later.

To disable this behavior, set the DISABLE_SOURCE_REPLACEMENT environment variable to true in your MCP configuration:

{
  "mcpServers": {
    "data-extractor": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-data-extractor"
      ],
      "env": {
        "DISABLE_SOURCE_REPLACEMENT": "true"
      },
      "disabled": false,
      "autoApprove": [
        "extract_data",
        "extract_svg"
      ]
    }
  }
}

Supported Patterns

Data Extraction Patterns

The data extractor supports various patterns commonly used in TypeScript/JavaScript applications:

  1. Simple Object Exports:

export default {
  welcome: "Welcome to our app",
  greeting: "Hello, {name}!",
  submit: "Submit form"
};
  1. Nested Objects:

export default {
  header: {
    title: "Book Your Flight",
    subtitle: "Find the best deals"
  },
  footer: {
    content: [
      "Please refer to {{privacyPolicyUrl}} for details",
      "© {{year}} {{companyName}}"
    ]
  }
};
  1. Complex Structures with Arrays:

export default {
  faq: {
    heading: "Common questions",
    content: [
      {
        heading: "What if I need to change my flight?",
        content: "You can change your flight online if:",
        list: [
          "You have a flexible fare type",
          "Your flight is more than 24 hours away"
        ]
      }
    ]
  }
};
  1. Template Literals with Variables:

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

Output Formats

Data Extraction Output

The extracted data is saved as a JSON file with dot notation for nested structures:

{
  "welcome": "Welcome to our app",
  "header.title": "Book Your Flight",
  "footer.content.0": "Please refer to {{privacyPolicyUrl}} for details",
  "footer.content.1": "© {{year}} {{companyName}}",
  "faq.content.0.heading": "What if I need to change my flight?"
}

SVG Extraction Output

SVG components are extracted into individual .svg files, with React-specific code removed. For example:

Input (React component):

const InspectionIcon: React.FC<InspectionIconProps> = ({ title }) => (
  <svg className="c-tab__icon" width="40px" id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32">
    <title>{title}</title>
    <path className="cls-1" d="M18.89,12.74a3.18,3.18,0,0,1-3.24-3.11..." />
  </svg>
);

Output (InspectionIcon.svg):

<svg width="40px" id="Layer_1" data-name="Layer 1" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 32 32">
    <path class="cls-1" d="M18.89,12.74a3.18,3.18,0,0,1-3.24-3.11..." />
</svg>

Extending Supported Patterns

The extractor uses Babel to parse and traverse the AST (Abstract Syntax Tree) of your source files. You can extend the supported patterns by modifying the source code:

  1. Add New Node Types: The extractStringValue method in src/index.ts handles different types of string values. Extend it to support new node types:

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 here
  return null;
}
  1. Custom Value Processing: The processValue method handles different value types (strings, arrays, objects). Extend it to support new value types or custom processing:

private processValue(value: t.Node, currentPath: string[]): void {
  if (t.isStringLiteral(value) || t.isTemplateLiteral(value)) {
    // Process string values
  } else if (t.isArrayExpression(value)) {
    // Process arrays
  } else if (t.isObjectExpression(value)) {
    // Process objects
  }
  // Add support for new value types here
}
  1. Custom AST Traversal: The server uses Babel's traverse to walk the AST. You can add new visitors to handle different node types:

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

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Available Tools

2 tools
extract_dataA

Extract data content (e.g. i18n translations) from source code to a JSON file. IMPORTANT: When encountering files with data such as i18n content embedded in code, use this tool directly instead of reading the file content first. This tool will programmatically extract all translations into a structured JSON file, preserving nested objects, arrays, template variables, and formatting. This helps keep translations as configuration and prevents filling up the AI context window with translation content. By default, the source file will be replaced with "MIGRATED TO " and a warning message after successful extraction, making it easy to track where the data was moved to. This behaviour can be disabled by setting the DISABLE_SOURCE_REPLACEMENT environment variable to 'true'. The warning message can be customized by setting the WARNING_MESSAGE environment variable.

Inputs: sourcePath (required), targetPath (required).

extract_svgA

Extract SVG components from React/TypeScript/JavaScript files into individual .svg files. This tool will preserve the SVG structure and attributes while removing React-specific code. By default, the source file will be replaced with "MIGRATED TO " and a warning message after successful extraction, making it easy to track where the SVGs were moved to. This behaviour can be disabled by setting the DISABLE_SOURCE_REPLACEMENT environment variable to 'true'. The warning message can be customized by setting the WARNING_MESSAGE environment variable.

Inputs: sourcePath (required), targetDir (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools target clearly distinct extraction types: structured data (e.g. i18n translations) versus SVG components. An agent can easily choose between them based on the file/content type, with no meaningful overlap.

    Naming Consistency5/5

    Both tools follow the same verb_noun pattern: extract_data and extract_svg. The naming is simple, predictable, and directly reflects the output type.

    Tool Count4/5

    At two tools, the server is slightly below the typical well-scoped range, but the count is reasonable for a narrowly focused extractor utility. Each tool covers a distinct extraction workflow and earns its place.

    Completeness4/5

    The server covers its stated domain reasonably well: data extraction and SVG extraction are both implemented with source-replacement behavior. It is a small surface, but there are no obvious dead ends within the apparent scope of a specialized extractor.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      B
      quality
      D
      maintenance
      A basic TypeScript implementation of the Model Context Protocol (MCP) server designed as a starting point for MCP development. Provides a minimal foundation for building custom MCP servers with stdio configuration for local integration with VS Code and GitHub Copilot.
      1
      -
    • F
      license
      B
      quality
      D
      maintenance
      A Model Context Protocol server that builds and queries a config-aware code graph with support for conditional compilation (#ifdef) filtering, enabling context-aware code analysis across different build configurations.
      9
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server that parses code, documents, data, and config files into structured database snapshots for targeted AI retrieval, enabling code analysis and project understanding via LLM interactions.
      1
      -