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
g0t4/mcp-server-commands
The project "mcp-server-commands" is an MCP (Model Context Protocol) server designed to enable large language models (LLMs) to securely execute shell commands and interact with the system environment. It provides a single command interface called `run_command` that allows LLMs to run various shell commands such as `hostname`, `ls -al`, or `echo "hello world"`. The server returns the standard output (STDOUT) and standard error (STDERR) as text, and it supports an optional `stdin` parameter to pass code or text input to commands like shells (fish, bash, zsh) or interpreters (python). This feature also allows creating files by redirecting input to files. The server is designed with security in mind, warning users to be cautious about the commands they allow the LLM to run. It is recommended to use the "Approve Once" option in the Claude Desktop app to review each command before execution and to avoid running the server with elevated privileges like `sudo`. The server integrates with various LLMs and tools, including Claude Sonnet 3.5, Groq Desktop with MCP, and llama4 models, showing promising results in initial testing. Installation and usage instructions are provided for different platforms, including MacOS and Windows, with configuration examples for Claude Desktop and Groq Desktop. The project is published as an npm package and can also be built locally from the source. It supports communication over the STDIO transport and can be bridged to HTTP using the `mcpo` tool for OpenAPI compatibility, enabling integration with web interfaces like Open-WebUI. The project includes logging and debugging support, with logs written to STDERR and an MCP Inspector tool available for debugging MCP server communications. It also provides guidance on using local models with the server and emphasizes the importance of security and careful command approval when using the server in practice.
https://github.com/g0t4/mcp-server-commands
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.