sjkim1127/Reversecore_MCP ? reverse-engineered prompt

Build me a security first MCP server that lets an AI assistant inspect suspicious files and source code in plain English.

I want to be able to point it at a binary, script, memory image, or packet capture and ask things like decompile this, pull out strings and indicators, check for malware behavior, map findings to MITRE ATT&CK, look for vulnerable code patterns, and produce a clean triage report. It should support reverse engineering, malware analysis, digital forensics, vulnerability research, and simple source auditing, with structured results the AI can chain together.

Please include the main analysis capabilities you’d expect for this kind of project, like Radare2 based binary analysis, YARA scanning, LIEF parsing, Capstone disassembly, and a few guided analysis modes and report templates. Make it safe by default, validate inputs carefully, and keep it easy to run locally or in Docker. If you need current setup details from the docs, look them up online.