BinAssist (Binary Ninja)

BinAssistMCP provides a complete bridge between Binary Ninja and Large Language Models through dual transport support (SSE and STDIO), enabling AI-assisted reverse engineering workflows. Built by Jason Tang using Python with FastMCP, it exposes over 40 Binary Ninja tools including decompilation, IL analysis, symbol management, type system manipulation, and cross-reference analysis, while supporting multi-binary sessions with automatic context management. The implementation integrates directly as a Binary Ninja plugin with auto-startup capabilities and configurable settings, making it valuable for security researchers, malware analysts, and reverse engineers who want to leverage AI assistance for binary analysis tasks like vulnerability research, code understanding, and automated documentation generation.

Source

Repository: https://github.com/symgraph/binassistmcp