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
DMontgomery40/pentest-mcp
pentest-mcp is a Model Context Protocol server that wraps a broad set of penetration-testing and reconnaissance utilities so AI coding and security agents can run them as MCP tools. Written in JavaScript and distributed on npm, it exposes tools including nmapScan, subfinderEnum, httpxProbe, ffufScan, nucleiScan, gobuster, nikto, hydraBruteforce, runJohnTheRipper, runHashcat, trafficCapture, privEscAudit, extractionSweep and generateWordlist, covering network scanning, web probing, fuzzing, vulnerability scanning, brute forcing and password cracking. It supports several transports: stdio for local clients, Streamable HTTP as the recommended network transport, and a deprecated SSE compatibility mode. For networked deployments it adds bearer-token authentication with OIDC JWKS verification and token introspection, configured through environment variables. The server also includes an engagement workflow: every tool run stores a structured record with invocation context, and reporting tools such as listEngagementRecords, getEngagementRecord and createClientReport let agents assemble client reports. A statement-of-work capture flow uses MCP elicitation to prompt for scope interactively, accept pasted scope text, or fall back to a safe generic authorized-testing template. It bundles the MCP Inspector through a launcher command and hardens command resolution to avoid collisions with the Python httpx CLI. It targets security professionals who want to drive recon and testing tooling through an AI agent while keeping structured records for reporting. Users are expected to operate it only against systems they are authorized to test.
https://github.com/DMontgomery40/pentest-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.