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
MorDavid/BloodHound-MCP-AI
BloodHound-MCP-AI is an innovative integration that connects BloodHound, a leading tool for Active Directory security analysis, with AI capabilities through the Model Context Protocol (MCP). This integration enables security professionals to interact with BloodHound data using natural language queries, simplifying the complex process of analyzing Active Directory attack paths. By leveraging the MCP Server, BloodHound-MCP allows users to perform detailed security assessments and discover intricate attack vectors within Active Directory environments more efficiently. The project combines three core components: BloodHound, MCP, and Neo4j. BloodHound provides the foundational data and visualization of Active Directory relationships and attack paths. MCP serves as an open protocol that facilitates the creation of custom AI tools compatible with various AI models, enabling natural language processing capabilities. Neo4j is the graph database that stores the Active Directory data used by BloodHound. BloodHound-MCP includes over 75 specialized tools based on original BloodHound Cypher queries, covering a wide range of security analysis categories such as domain structure mapping, privilege escalation paths, Kerberos security issues (including Kerberoasting and AS-REP Roasting), certificate services vulnerabilities, Active Directory hygiene, NTLM relay attack vectors, and delegation abuse opportunities. Users can generate comprehensive security reports and gain insights into potential vulnerabilities and attack paths. The project requires BloodHound 4.x or higher with data collected from an Active Directory environment, a Neo4j database loaded with BloodHound data, Python 3.8 or higher, and an MCP client. Installation involves cloning the repository, installing dependencies, and configuring the MCP server with appropriate credentials. BloodHound-MCP-AI is designed for authorized security assessments and emphasizes responsible use and data handling. It is a community-driven project licensed under the MIT License and supported by a community Telegram channel for updates and discussions. This integration represents the first-ever connection of BloodHound with AI through MCP, enhancing the accessibility and effectiveness of Active Directory security analysis.
https://github.com/MorDavid/BloodHound-MCP-AI
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.