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
netwrix/mcp-server-naa
Netwrix Access Analyzer MCP Server is a Python MCP server that puts the results of Netwrix Access Analyzer scans in reach of an AI assistant, with Claude Desktop as the documented client. It does not perform scans itself: it connects to the SQL Server database where Access Analyzer stores completed Active Directory and File System scan results, and reads from the views that product publishes. Connection happens automatically at startup from environment variables that carry the server host, database name, credentials and a flag for Windows authentication, and additional tools let a session connect to a different database, show current connection status and inspect a table schema, so the database structure can be explored dynamically. On the Active Directory side the tools cover effective group membership with filters, AD exceptions, permissions from the permissions view, domain controller listings, certificate vulnerabilities, certificate authority rights, a general AD security assessment, and detail lookups for users, groups and computers. On the File System side the tools find where sensitive data lives through data loss prevention matches, list open shares reachable by broad groups, show which resources a given trustee can reach and where that access comes from, report effective access for a resource path, surface users holding unused access to a share, list running Access Auditor jobs and report shadow access. Requirements are Python 3.12 or newer, the MCP SDK, pyodbc, python-dotenv and an ODBC driver for SQL Server installed on the host machine; the server is launched through uv and registered in the Claude Desktop MCP configuration. The audience is identity and access governance staff who already run Netwrix Access Analyzer and want to interrogate permission and exposure findings in natural language rather than through report queries.
https://github.com/netwrix/mcp-server-naa
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.