Browse the library

This MCP server enables AI agents to autonomously perform penetration testing, vulnerability discovery, and bug bounty automation using over 150 cybersecurity tools.

A Claude Code plugin marketplace from Trail of Bits, offering skills to enhance AI-assisted security analysis, vulnerability detection, and audit workflows.

This MCP server enables an AI agent to perform penetration testing, investigate applications, record findings, and verify exploits with evidence.

This production-grade MCP server gives Claude 27 security intelligence tools across 21 APIs for CVE lookup, EPSS scoring, CISA KEV, and more, enabling rapid security analysis.

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

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.

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 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.

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 CLI scans AI agent skills, MCP server configs, and IDE rule files to detect security threats, privacy violations, and instruction-level attacks.

This tool runs AI coding agents like Claude Code inside a bubblewrap sandbox, limiting their access to only the current working directory for enhanced security.