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
VirusTotal MCP Server exposes VirusTotal, the multi-engine malware and reputation scanning service, to MCP clients. Its tools take the four indicator types VirusTotal covers — a URL, a file hash, an IP address or a domain — and return the aggregated verdicts of the antivirus engines and reputation sources, along with the metadata VirusTotal holds. Two design choices go beyond a thin API wrapper. Relationship data is fetched automatically, so a report on a domain also brings back the associated files, resolutions and URLs that VirusTotal links to it, letting a model pivot across an investigation without a separate call for each edge. Pagination is handled explicitly, which matters because relationship sets on well-known indicators are large and would otherwise be truncated silently. The server is TypeScript, published on npm as @burtthecoder/mcp-virustotal, listed in the MCP registry and on Smithery, and requires a VIRUSTOTAL_API_KEY; the README gives one-line install commands for Claude Code, Codex CLI, Gemini CLI and Claude Desktop. The audience is incident responders and malware analysts who work in indicators of compromise and want the enrichment step — check this hash, then check what else it touches — driven conversationally.
https://github.com/BurtTheCoder/mcp-virustotal
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.