mukul975/Anthropic-Cybersecurity-Skills
A comprehensive open-source library featuring 754 structured cybersecurity skills for AI agents, mapped to five industry frameworks to provide expert-level guidance.
Awesome MCP › Security & Reverse Engineering
ZoomEye MCP Server provides network asset intelligence from ZoomEye, a search engine that continuously scans and fingerprints internet-facing hosts. Its tools accept ZoomEye dorks — the query syntax that filters by service, software version, banner content, certificate details, geography and organisation — and return the matching assets with the details ZoomEye records: open ports, identified services and versions, response banners and location. That makes the usual reconnaissance sequence expressible in conversation: find all hosts running a given software version in a given country, then examine what else those hosts expose. Real-time tracking of changes is supported, so an assistant can report what has appeared or disappeared since a previous look, which is the useful shape for monitoring an organisation's own external attack surface. It is a Python project maintained by the ZoomEye team, so tool coverage tracks the platform, and it requires ZoomEye API credentials with a paid subscription beyond the free allowance. The dual-use nature is inherent to the tool class — the same query that inventories your own exposure inventories someone else's — so authorised use is the operator's responsibility. The audience is security teams doing external attack-surface management and threat intelligence.
https://github.com/zoomeye-ai/mcp_zoomeye
A comprehensive open-source library featuring 754 structured cybersecurity skills for AI agents, mapped to five industry frameworks to provide expert-level guidance.
NVIDIA security scanner for AI agent skills and MCP tooling that detects prompt injection, data exfiltration, MCP tool poisoning and least-privilege problems, and can itself be run as an MCP server inside agent sessions.
ida-pro-mcp is an MCP server for IDA Pro that enables advanced reverse engineering capabilities through MCP-based interactions and automation.
GhidraMCP is an MCP server that integrates Ghidra's reverse engineering capabilities with MCP clients, enabling automated binary analysis and decompilation through large language models.
MCP-Scan is a security tool that statically and dynamically scans and monitors Model Context Protocol (MCP) connections to detect and prevent vulnerabilities such as prompt injections, tool poisoning, and cross-origin escalations.
JADX-AI-MCP is a JADX plugin integrating Model Context Protocol to enable AI-powered live reverse engineering, vulnerability detection, and code analysis of Android APKs using large language models like Claude.
Beelzebub is a secure low-code honeypot framework leveraging large language models and the Model Context Protocol (MCP) to detect and analyze cyber attacks, including prompt injection attempts against LLM agents.
mcp-windbg is a Model Context Protocol server that enables AI models to analyze Windows crash dumps using WinDBG through natural language interaction and command execution.