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
securityfortech/secops-mcp
Security Operations Multi-Tool Platform is a Python server that puts a collection of well known offensive security and reconnaissance tools behind a single interface, so scans can be launched through one entry point and results come back in a consistent JSON envelope with a success flag, an optional error message and a results object. The bundled tools cover several areas. For web application testing it exposes Nuclei for template driven vulnerability scanning, FFUF and WFuzz for fuzzing and content discovery, Dirsearch for directory and file enumeration, XSStrike for cross site scripting detection and exploitation, SQLMap for SQL injection testing, Arjun for hidden HTTP parameter discovery and Gospider for crawling and URL discovery. For network work it provides Nmap for host and service enumeration, HTTPX as a general HTTP probing toolkit and TLSX for TLS configuration analysis. For reconnaissance it includes Amass for attack surface mapping and external asset discovery, Subfinder for subdomain enumeration and IPInfo for address intelligence. Hashcat covers password recovery and hash analysis. Each tool is wrapped by a module in the tools directory, and those wrappers hold the configuration surface: output formats, timeouts, verbosity levels, custom wordlists and tool specific parameters. Documented examples show Gospider crawling with a configurable depth, optional subdomain inclusion and extension based include or exclude filters, plus form detection and flagging of potentially sensitive strings, and Arjun discovering parameters over GET, POST or other methods with custom data, a stable mode that reduces false positives, custom headers for authentication, configurable threading and bulk scanning of several URLs at once. The recommended deployment is the provided Dockerfile, which avoids installing every scanner by hand; a manual install with a virtual environment is also documented but requires each external tool on PATH. The README stresses that the platform is for authorised testing only.
https://github.com/securityfortech/secops-mcp
Also in Security & Reverse Engineering
NVIDIA/SkillSpector
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.
mrexodia/ida-pro-mcp
ida-pro-mcp is an MCP server for IDA Pro that enables advanced reverse engineering capabilities through MCP-based interactions and automation.
LaurieWired/GhidraMCP
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.
invariantlabs-ai/mcp-scan
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.
zinja-coder/jadx-ai-mcp
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.
mariocandela/beelzebub
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.
svnscha/mcp-windbg
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.