reverse-engineering-assistant and Reversecore_MCP

These are complements—the first provides basic Ghidra integration for reverse engineering tasks, while the second extends the capability by orchestrating multiple specialized tools (Ghidra, Radare2, YARA) together with security-focused automation, allowing them to be used in tandem for more comprehensive analysis workflows.

Reversecore_MCP
46
Emerging
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 16/25
Maintenance 10/25
Adoption 8/25
Maturity 13/25
Community 15/25
Stars: 629
Forks: 56
Downloads:
Commits (30d): 17
Language: Java
License: Apache-2.0
Stars: 49
Forks: 8
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About reverse-engineering-assistant

cyberkaida/reverse-engineering-assistant

MCP server for reverse engineering tasks in Ghidra 👩‍💻

Exposes Ghidra's analysis capabilities as an MCP server with a tool-driven architecture designed for long-form LLM reasoning, using fragmented context and cross-reference guidance to reduce hallucination. Operates in both assistant mode (interactive analysis with Claude Code/VSCode via HTTP transport) and headless mode (CI/CD automation, Docker, PyGhidra integration). Interoperates with other MCP servers like GitHub and Kagi to augment reverse engineering analysis with external sources.

About Reversecore_MCP

sjkim1127/Reversecore_MCP

A security-first MCP server empowering AI agents to orchestrate Ghidra, Radare2, and YARA for automated reverse engineering.

Implements a FastMCP-based stdio transport with connection pooling for Radare2 and automatic Ghidra-to-r2 fallback strategies, while providing specialized malware analysis features like dormant threat detection, IOC extraction, and adaptive vaccine generation. Integrates with MCP clients (Cursor, Claude Desktop) via Docker containers with workspace mounting, includes 700+ unit tests and a web dashboard for standalone binary analysis without LLM dependencies.

Scores updated daily from GitHub, PyPI, and npm data. How scores work