Deobfuscate MCP Server
D

Deobfuscate MCP Server

An MCP server optimized for large language models, used for deobfuscating, unpacking, and navigating compressed and packaged JavaScript code, helping LLM understand complex code structures and save the context window.
2.5 points
6.0K

What is Deobfuscate MCP Server?

This is a tool specifically designed to help AI models understand and analyze compressed and obfuscated JavaScript code. Different from traditional code beautification tools, it treats the compressed code as a searchable database, allowing AI to access specific parts on demand instead of loading the entire large file at once.

How to use Deobfuscate MCP Server?

First, install the server via npm or build it from the source code. Then, configure the MCP server in your AI client (such as Claude, Gemini, etc.). After the configuration is completed, the AI can analyze the code through specific tool calls: first unpack the code, view the structure summary, and then delve into specific modules or functions as needed.

Use cases

It is particularly useful when you need to analyze compressed, obfuscated, or packaged JavaScript code, for example: analyzing the implementation of third - party libraries, debugging compressed code in the production environment, understanding complex Webpack - packaged applications, or researching obfuscated security code.

Main features

Code deobfuscation and unpacking
Use the webcrack tool to unpack Webpack/Browserify - packaged code, split a single compressed file into multiple independent modules, and support options such as skipping vendor code, shortening variable names, and restoring JSX syntax.
Code structure analysis
Generate a high - level structure summary of the code, including information such as functions, classes, and exports, to help AI quickly understand the code architecture without having to read the entire source code.
Modular navigation
List all unpacked modules and allow on - demand access to the source code of specific modules, avoiding loading the entire large file at once.
Function analysis
Scan all modules, list the defined functions and classes and their signatures and parameters, to help AI quickly locate specific functions.
Call graph
Generate a call graph for a specific function, showing which other functions are called by this function and which functions call it.
Symbol extraction
Extract the source code of specific functions, classes, or variables, and only return the relevant parts to save the AI's context space.
Semantic search
Perform regular expression or string search in all unpacked modules to quickly locate specific code patterns.
Code formatting
Use Prettier to standardize and format JavaScript, HTML, and CSS code.
Advantages
Save AI context space: Avoid loading the entire large file through modular access
Improve analysis efficiency: AI can quickly understand the code structure and then delve into specific parts
Intelligent search: Support semantic search across all modules to quickly locate code
Easy to integrate: Support mainstream AI clients (Claude, Gemini, Antigravity)
Rich functions: Provide a full - set of tools from unpacking to call relationship analysis
Limitations
File size limit: Maximum support for an input file of 50MB
Memory consumption: Unpacked modules are cached in memory, and very large files may consume more memory
Specific format: Mainly for JavaScript packaging formats (Webpack/Browserify)
Requires configuration: Additional configuration is required in the AI client

How to use

Install the server
Install the server globally via npm, or build and package it from the source code.
Configure the AI client
According to the AI client you are using (Claude, Gemini, or Antigravity), add the corresponding MCP server configuration.
Start analysis
Provide the compressed JavaScript code in the AI conversation, and the AI will automatically call the corresponding tools for analysis.
Explore in depth
Based on the structure summary provided by the AI, request to view specific modules, functions, or perform searches.

Usage examples

Analyze compressed production - environment code
When you need to analyze a compressed and obfuscated production - environment JavaScript file, you can use this tool to gradually understand the code structure.
Find the implementation of a specific function
When you need to find the implementation of a specific function (such as login logic) in a large compressed codebase.
Understand the function call relationship
When you need to understand the call relationship of a specific function in the entire codebase.

Frequently Asked Questions

Which JavaScript packaging formats does this tool support?
Why do we need an MCP server instead of directly letting the AI analyze the code?
Where will the unpacked code be stored?
What is the supported file size?
How to run from the source code instead of a global installation?

Related resources

GitHub repository
Source code and the latest version
npm package page
npm installation package information
Model Context Protocol documentation
Official documentation of the MCP protocol
webcrack tool
Underlying JavaScript unpacking tool used

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "deobfuscate-mcp-server": {
      "command": "npx",
      "args": ["-y", "deobfuscate-mcp-server"]
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
9.1K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
10.9K
4.5 points
B
Bm.md
A feature-rich Markdown typesetting tool that supports multiple style themes and platform adaptation, providing real-time editing preview, image export, and API integration capabilities
TypeScript
17.6K
5 points
S
Security Detections MCP
Security Detections MCP is a server based on the Model Context Protocol that allows LLMs to query a unified security detection rule database covering Sigma, Splunk ESCU, Elastic, and KQL formats. The latest version 3.0 is upgraded to an autonomous detection engineering platform that can automatically extract TTPs from threat intelligence, analyze coverage gaps, generate SIEM-native format detection rules, run tests, and verify. The project includes over 71 tools, 11 pre-built workflow prompts, and a knowledge graph system, supporting multiple SIEM platforms.
TypeScript
9.4K
4 points
P
Paperbanana
Python
9.6K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
9.2K
4.5 points
A
Assistant Ui
assistant - ui is an open - source TypeScript/React library for quickly building production - grade AI chat interfaces, providing composable UI components, streaming responses, accessibility, etc., and supporting multiple AI backends and models.
TypeScript
9.7K
5 points
A
Apify MCP Server
The Apify MCP Server is a tool based on the Model Context Protocol (MCP) that allows AI assistants to extract data from websites such as social media, search engines, and e-commerce through thousands of ready-to-use crawlers, scrapers, and automation tools (Apify Actors). It supports OAuth and Skyfire proxy payment and can be integrated into MCP clients such as Claude and VS Code through HTTPS endpoints or local stdio.
TypeScript
9.7K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
23.9K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
29.5K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
40.5K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
82.7K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
71.9K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
39.3K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
24.1K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
110.5K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase