Browse the library

This MCP bridge connects AI agents to Cheat Engine, enabling natural language automation of reverse engineering, pointer scanning, and memory analysis.

A self-hosted sandbox for red teams to analyze malware payloads, with MCP integration for LLM-driven analysis.

An open-source AI reverse-engineering agent platform and MCP server for automated binary analysis, CTF, and malware research.

Skills from Pashov Audit Group that run Solidity security audits, pre-audit x-ray scans and Echidna/Medusa fuzz suite generation.

This security scanner analyzes LLM agentic workflows, identifies tools and MCP servers, and maps potential vulnerabilities for security insights.

A security-oriented runtime that executes WebAssembly Components via MCP, providing browser-grade isolation for AI agent tools.

An MCP server that provides attestation infrastructure for AI agents, including DID-based identity, W3C Verifiable Credentials, and an EU AI Act compliance layer with 47 tools.

An MCP server that enables AI agents to perform headless reverse engineering with IDA Pro, optimized for Apple targets and fast analysis.

A Ghidra MCP server that provides AI agents with a tool-driven approach for reverse engineering, designed to reduce context rot and improve long-form analysis.

This MCP server connects AI agents to a Linux machine, enabling them to execute terminal commands and perform AI-assisted penetration testing tasks.

A powerful Rust-based Solidity static analyzer that integrates with AI agents via MCP to find vulnerabilities in smart contracts.

A collection of 38 Dockerized MCP servers offering 300+ offensive security tools like Nmap and Ghidra, enabling AI agents to perform security assessments.

An MCP server that integrates with the JADX-AI Plugin, enabling LLMs like Claude to analyze Android APKs for vulnerabilities and perform reverse engineering tasks.

GhidrAssistMCP is a Ghidra extension that provides an MCP server, allowing AI assistants to interact with Ghidra's reverse engineering tools and data.

An awesome list providing comprehensive resources and considerations for Model Context Protocol (MCP) security, including best practices for servers and clients.

Local safety gate and memory for agents that blocks destructive commands like rm -rf via a PreToolUse hook and traces failures to their root cause.

A secure runtime for AI agents that enforces English-language security policies to prevent unauthorized file or network access.

Authority gate that checks approvals before an agent's protected tool runs, binding approval to exact details like amount and destination, with verifiable evidence.

This provides ready-to-use hooks for Claude Code, shipped as a 22-plugin marketplace, enforcing least privilege for agent actions like safety and automation.

Agent Skills for browser fingerprint testing, allowing an agent to run liarjs to score a browser's consistency across various probes.

This toolkit provides Claude Code plugins to transform technical evidence into GRC compliance artifacts like gap reports, remediation guidance, and OSCAL workflows.

This plugin provides security controls for AI agents, enforcing policies, scanning vulnerabilities, and tracking drift to prevent unintended actions.

This plugin offers a spec-driven offensive security framework for Claude Code, including kill-chain skills, collaborative agents, and a vulnerability reference library.

Provides essential security rules for Cursor to enforce safe coding practices and prevent sensitive operations in AI-assisted development.