Recafmcp
An open - source plugin that allows AI assistants to control the Recaf 4.x bytecode analysis tool through the Model Context Protocol (MCP). It supports 25 tools such as decompiling, searching, analyzing, editing bytecode, compiling Java, assembling/disassembling JASM, comparing classes, patching, and exporting JARs.
2.5 points
5.0K

What is the Recaf MCP Plugin?

The Recaf MCP Plugin is a bridge that connects AI assistants with the Recaf bytecode analysis tool. It allows you to directly control Recaf through natural language instructions (such as AI assistants like Claude and Cursor) to perform operations such as decompiling, searching, editing, compiling, and exporting Java bytecode. There's no need to manually operate the Recaf interface, and the AI can help you complete complex reverse engineering tasks.

How to use the Recaf MCP Plugin?

The usage is divided into three simple steps: 1) Start Recaf with the plugin. 2) Configure the MCP server in the AI client. 3) Control Recaf through natural language instructions. The plugin adopts a dual - process architecture: one plugin runs an HTTP server inside Recaf, and another independent MCP server communicates with the AI and forwards requests.

Applicable scenarios

It is applicable to scenarios such as Java reverse engineering, code analysis, security auditing, malware analysis, code obfuscation/de - obfuscation, multi - version comparison, and automated patch generation. It is especially suitable for developers and security researchers who need to frequently analyze, modify, and export Java bytecode.

Main features

Workspace management
Supports opening multiple JAR/APK/Class files simultaneously, allows switching between different workspaces, and provides class list browsing and file reading functions.
Code analysis
Decompile Java bytecode into readable source code, search for strings, references, and declarations, view method call graphs and class inheritance relationships, and compare code differences between different versions.
Bytecode editing
Rename classes/fields/methods (automatically update references), add/delete/modify methods and fields, and view detailed bytecode instruction information.
Compilation and assembly
Compile Java source code and apply it to the workspace, disassemble bytecode into JASM text format, and support assembling JASM back to bytecode.
Export and patching
Export rename mappings, modified JAR files, and decompiled source code, and create and apply workspace change patches.
Multi - workspace support
Allows analyzing multiple JAR files simultaneously, enables quick switching between different workspaces, facilitating comparative analysis and batch processing.
Advantages
Natural language interaction: Control complex bytecode operations through natural language using AI assistants, reducing the learning cost.
Comprehensive functions: 25 tools cover the complete workflow from analysis to editing and then to export.
Two - way integration: Utilize both the intelligent analysis capabilities of AI and the professional bytecode processing engine of Recaf.
Efficient workflow: Automate repetitive tasks such as batch renaming, search and replace, and code comparison.
Technology stack compatibility: Supports JDK 22+ and keeps in sync with the latest Java versions.
Limitations
Dependence on Recaf: Requires installing and running the Recaf 4.x desktop application.
Configuration steps: Need to configure both the Recaf plugin and the MCP server of the AI client.
Learning curve: Although it simplifies operations, still requires understanding basic Java bytecode concepts.
Performance overhead: The dual - process architecture increases certain system resource consumption.
Network dependence: The Bridge Server uses local HTTP communication, which may be restricted in some security environments.

How to use

Environment preparation
Install JDK 22 or a higher version and ensure the java command is available. Download or build the Recaf MCP Plugin.
Start the Recaf plugin
Put the plugin JAR file into the plugins directory of Recaf, or directly run it using gradle. After starting Recaf, confirm that the plugin is loaded successfully.
Configure the AI client
Configure the MCP server in AI clients that support MCP, such as Claude Code and Cursor, and point to the independent MCP Server JAR file.
Start using
Restart the AI client, and the Recaf tool will appear in the list of available tools. Now you can control Recaf through natural language instructions.

Usage cases

Reverse analysis of an obfuscated JAR file
Analyze an obfuscated Java application, understand its functions, and rename key classes and methods.
Compare the differences between two versions of an application
Compare the bytecode differences between the old and new versions of an application and find out the modified content.
Modify bytecode to add debugging functions
Add debugging fields and methods to the existing bytecode for runtime monitoring.
Compile custom Java code into an existing workspace
Write new Java classes or modify existing classes and directly compile them into the opened JAR workspace.

Frequently Asked Questions

Why do I need to run both Recaf and the AI client simultaneously?
Which AI clients are supported?
What should I do if opening a JAR file fails?
What format should the class name use?
How to save the modified content?
The decompilation result is incomplete or incorrect?
Can I analyze multiple JARs simultaneously?
What should I do if compiling Java code fails?

Related resources

Recaf official repository
Source code and documentation of the Recaf bytecode editor
Model Context Protocol official website
Official documentation and specifications of the MCP protocol
Plugin GitHub repository
Source code and latest version of the Recaf MCP Plugin
Chinese documentation
Chinese usage instruction documentation of the plugin
Gradle build tool
Build tool used in the project
ASM bytecode framework
Bytecode operation framework used by Recaf

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "recaf": {
      "command": "java",
      "args": ["-jar", "/absolute/path/to/build/mcp/recaf-mcp-server-1.2.0.jar"]
    }
  }
}
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
4.9K
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
5.5K
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
3.9K
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
6.3K
4 points
P
Paperbanana
Python
7.5K
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
6.1K
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
7.6K
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
7.4K
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
24.7K
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
34.6K
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
72.6K
4.3 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
20.5K
4.5 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
63.8K
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#
31.5K
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
21.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
49.5K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase