hqkh4nh

dejared-mcp

Community hqkh4nh
Updated

A MCP server for exploring, analyzing, and decompiling Java JAR files

npm versionLicense: MITNode.jsJava

dejared-mcp

A Model Context Protocol (MCP) server for exploring, analyzing, and decompiling Java JAR files.Designed for AI-powered development tools, dejared-mcp connects your IDE or CLI assistantto inspect package structures, search bytecode, and decompile classesusing CFR, Vineflower, or Procyon.

Table of Contents

  • Overview
  • Prerequisites
  • Quick Start
  • Features
  • Decompiler Engines
  • Installation and Configuration
  • Custom Java Path
  • Server Configuration
  • How It Works
  • FAQ and Troubleshooting
  • Contributing
  • Third-Party Licenses
  • License

Overview

dejared-mcp is a Java-based MCP server distributed as an npm package.It provides nine tools organized into three categories: discovery, hunting,and deep analysis. AI assistants use these tools to navigate JAR filestructures, search for classes and string literals in bytecode, anddecompile .class files back to readable Java source code.

The npm package acts as a thin wrapper that downloads and caches theserver JAR on first run, then spawns it via java -jar using stdiotransport.

Prerequisites

  • Node.js 18 or later
  • Java 17 or later (JRE is sufficient)

Quick Start

Add the following to your MCP client configuration:

{
  "mcpServers": {
    "dejared": {
      "command": "npx",
      "args": ["-y", "dejared-mcp"]
    }
  }
}

See Installation and Configurationfor tool-specific instructions.

Features

Discovery

Browse and read JAR contents.

Tool Description
dejared_list_packages List all packages with class counts
dejared_list_classes List classes in a specific package
dejared_list_resources List non-class resource files
dejared_read_resource Read text resources (YAML, XML, properties, JSON, and others)

Hunting

Search inside JAR files.

Tool Description
dejared_search_class Search classes by name
dejared_search_string Search string literals in bytecode (URLs, SQL, error messages)

Deep Analysis

Inspect metadata and decompile classes.

Tool Description
dejared_get_metadata Extract class metadata via ASM (fast, no decompilation)
dejared_dump_package_metadata Batch metadata extraction for entire packages
dejared_decompile_class Decompile .class files to Java source code

Decompiler Engines

dejared-mcp supports three decompiler engines. The engine can bespecified per request via the dejared_decompile_class tool.

Engine Description
CFR (default) Reliable general-purpose decompiler
Vineflower Modern fork of FernFlower, handles newer Java features well
Procyon Alternative engine, can handle some edge cases better

Installation and Configuration

The standard configuration below works with most MCP-compatible tools.Expand the relevant section for tool-specific instructions.

{
  "mcpServers": {
    "dejared": {
      "command": "npx",
      "args": ["-y", "dejared-mcp"]
    }
  }
}
Amp

Add via the Amp VS Code extension settings screen or by updating your settings.json file:

"amp.mcpServers": {
  "dejared": {
    "command": "npx",
    "args": ["-y", "dejared-mcp"]
  }
}

Amp CLI:

amp mcp add dejared -- npx -y dejared-mcp
Antigravity Editor

Edit ~/.gemini/antigravity/mcp_config.json:

{
  "mcpServers": {
    "dejared": {
      "command": "npx",
      "args": ["-y", "dejared-mcp"]
    }
  }
}

Or install through the MCP Store if available.

Claude Code
claude mcp add dejared -- npx -y dejared-mcp

Or add it to your project's .mcp.json using the standard config above.

Plugin (Marketplace) installs both the MCP server and the /jar-analysis skill:

claude plugin marketplace add hqkh4nh/dejared-mcp
claude plugin install dejared@dejared-mcp-marketplace
Claude Desktop

Edit the Claude Desktop config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the standard config above and restart Claude Desktop.

Cline

Add the standard config above to your MCP settings file.

Codex
codex mcp add dejared npx "-y dejared-mcp"

Or edit ~/.codex/config.toml:

[mcp_servers.dejared]
command = "npx"
args = ["-y", "dejared-mcp"]
Copilot CLI

Interactive:

/mcp add

Then fill in:

  • Server Name: dejared
  • Server Type: STDIO
  • Command: npx -y dejared-mcp

Or edit ~/.copilot/mcp-config.json:

{
  "mcpServers": {
    "dejared": {
      "type": "local",
      "command": "npx",
      "args": ["-y", "dejared-mcp"],
      "tools": ["*"]
    }
  }
}
Cursor

Create or edit .cursor/mcp.json in your project root (project-level) or ~/.cursor/mcp.json (global) using the standard config above.

Gemini CLI
gemini mcp add dejared npx -y dejared-mcp

Or edit ~/.gemini/settings.json (global) or .gemini/settings.json (project) using the standard config above.

Use /mcp in a Gemini CLI session to verify the server is connected.

Goose

Go to Advanced settings > Extensions > Add custom extension. Name to your liking, use type STDIO, and set the command to npx -y dejared-mcp.

JetBrains IDEs

Go to Settings > Tools > AI Assistant > Model Context Protocol (MCP).

Click + Add and configure:

  • Name: dejared
  • Transport: Stdio
  • Command: npx
  • Arguments: -y dejared-mcp
Kiro

Create or edit .kiro/settings/mcp.json using the standard config above.

opencode

Edit ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dejared": {
      "type": "local",
      "command": ["npx", "-y", "dejared-mcp"],
      "enabled": true
    }
  }
}
Qodo Gen

Open Qodo Gen chat panel in VS Code or IntelliJ > Connect more tools > + Add new MCP > Paste the standard config above > Save.

VS Code (GitHub Copilot)

Create or edit .vscode/mcp.json in your project root:

{
  "servers": {
    "dejared": {
      "command": "npx",
      "args": ["-y", "dejared-mcp"]
    }
  }
}

After saving, click the Start button that appears in the MCP config file, then use Agent mode in Copilot Chat.

Windsurf

Open Windsurf settings, navigate to MCP servers, and add a new server using the command type with npx -y dejared-mcp. Or add the standard config under mcpServers in your settings.

Pure Java (no Node.js required)

If you prefer to run the server JAR directly without Node.js:

  1. Download the latest JAR from GitHub Releases.

  2. Run it:

    java -jar dejared-mcp-0.2.0.jar
    
  3. Configure your MCP client to use the JAR directly instead of npx:

    {
      "mcpServers": {
        "dejared": {
          "command": "java",
          "args": ["-jar", "/path/to/dejared-mcp-0.2.0.jar"]
        }
      }
    }
    

Custom Java Path

If Java is not in your system PATH, set the DEJARED_JAVA_PATH environment variable in your MCP config. This applies to all npx-based configurations:

{
  "mcpServers": {
    "dejared": {
      "command": "npx",
      "args": ["-y", "dejared-mcp"],
      "env": {
        "DEJARED_JAVA_PATH": "/path/to/java"
      }
    }
  }
}

Server Configuration

Property Default Description
dejared.cache.max-size 500 Max entries in the decompilation LRU cache
dejared.security.max-resource-size 5242880 Max resource file size (bytes)
dejared.security.decompile-timeout-seconds 30 Timeout per decompilation

How It Works

The npm package is a thin Node.js wrapper. On first run it:

  1. Checks the platform cache directory for a cached JAR matching the current version.
    • Linux: $XDG_CACHE_HOME/dejared-mcp (defaults to ~/.cache/dejared-mcp)
    • macOS: ~/Library/Caches/dejared-mcp
    • Windows: %LOCALAPPDATA%\dejared-mcp
  2. Downloads the JAR from GitHub Releases if not cached.
  3. Spawns java -jar with stdio inherited for MCP transport.

The server communicates over stdio using the Model Context Protocol.

FAQ and Troubleshooting

Q: Java is installed but the server cannot find it.

Set the DEJARED_JAVA_PATH environment variable in your MCPconfiguration. See Custom Java Path.

Q: The server fails to start with a permission error.

Ensure that the cached JAR file is readable. The cache locationdepends on your platform. See How It Works forthe cache directory paths.

Q: Decompilation times out or returns an error.

Some classes are difficult to decompile. Try a different engineby specifying vineflower or procyon in the dejared_decompile_classtool. The default timeout is 30 seconds and can be adjusted viadejared.security.decompile-timeout-seconds.

Q: Which Java version do I need?

Java 17 or later. A JRE is sufficient; you do not need a full JDK.

Q: Can I run the server without Node.js?

Yes. Download the JAR from GitHub Releases and run it directlywith java -jar. See the "Pure Java" section underInstallation and Configuration.

Contributing

Contributions are welcome. Please follow these guidelines:

  1. Fork the repository and create a feature branch from master.
  2. Ensure your changes compile and pass existing tests.
  3. Write clear commit messages describing the purpose of each change.
  4. Open a pull request against master with a description of whatthe change does and why.

Project Structure

dejared-mcp/
├── bin/            # Node.js CLI entry point
├── lib/            # Node.js wrapper (JAR download and process management)
├── java-mcp/       # Java MCP server (Spring Boot, Gradle)
│   └── src/
├── skills/         # Claude Code plugin skills
├── package.json    # npm package manifest
└── server.json     # MCP Registry manifest

Building from Source

cd java-mcp
./gradlew build

Reporting Issues

Open an issue on GitHub Issueswith steps to reproduce the problem, your Java version, and yourNode.js version.

Third-Party Licenses

This project uses the following open-source libraries:

Library License
Spring Boot Apache 2.0
Spring AI Apache 2.0
ASM BSD 3-Clause
CFR MIT
Vineflower Apache 2.0
Procyon Apache 2.0

License

This project is licensed under the MIT License.

MCP Server · Populars

MCP Server · New

    jackccrawford

    Geniuz

    Your AI remembers now. Geniuz stores everything in a local database locally on Mac, Windows, Linux, Raspberry Pi. No cloud. No account. No API keys. Nothing leaves your machine. It's open source; you can read every line of code.

    Community jackccrawford
    ggui-ai

    ggui

    The universal interface layer between AI agents and humans. Generate rich UIs on demand via MCP.

    Community ggui-ai
    aanno

    CocoIndex Code MCP Server

    An RAG for code development, implemented as MCP server with cocoindex

    Community aanno
    timescale

    Tiger Linear MCP Server

    A wrapper around the Linear API for internal LLMs

    Community timescale
    choplin

    MCP Gemini CLI

    MCP Server

    Community choplin