Reversecore_MCP: Instructions file for Codex

Agent Customizations for Reversecore_MCP

This guide helps AI agents understand the codebase structure and be immediately productive.

Project Overview

Reversecore_MCP is an enterprise-grade MCP (Model Context Protocol) server for AI-powered reverse engineering. It enables AI agents to perform comprehensive binary analysis through natural language commands using Radare2, r2ghidra, and other industry-standard tools.

• Language: Python 3.10+
• Framework: FastMCP 2.13.1+
• Architecture: Layered (Prompts → Tools → Core Infrastructure → External Tools)
• Test Coverage: 55%+ with 700+ tests
• Key External Dependencies: Radare2 (disassembly/emulation), YARA (detection)

Quick Commands

Development Setup

# Create virtual environment
python -m venv venv
source venv/bin/activate  # Linux/macOS
venv\Scripts\activate     # Windows

# Install dependencies
pip install -r requirements.txt
pip install -r requirements-dev.txt

# Install pre-commit hooks (enforces code standards)
pre-commit install

Building & Running

# Start MCP server (development mode)
python server.py

# Docker (auto-detects architecture: Intel/ARM)
docker compose --profile x86 up -d    # Intel/AMD
docker compose --profile arm64 up -d  # Apple Silicon
./scripts/run-docker.sh                # Auto-detect

# Install external tools
./scripts/install-ghidra.sh            # Linux/macOS
.\scripts\install-ghidra.ps1           # Windows

Testing

# All tests (generates coverage report)
pytest tests/ -v

# Unit tests only
pytest tests/unit/ -v

# Integration tests
pytest tests/integration/ -v

# Specific test with coverage
pytest tests/unit/test_cli_tools.py::TestRunFile::test_success -v

# Check coverage threshold (must exceed 54%)
pytest --cov-report=term-missing

Code Quality

# Lint with Ruff
ruff check reversecore_mcp/

# Format with Black
black reversecore_mcp/

# Sort imports with isort
isort reversecore_mcp/

# Auto-fix all issues
ruff check --fix reversecore_mcp/
black reversecore_mcp/