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
Automata-Labs-team/code-sandbox-mcp
The project "code-sandbox-mcp" by Automata-Labs-team is an MCP (Model Context Protocol) server designed to provide a secure and isolated sandbox environment for executing code safely within AI applications. It leverages Docker containerization technology to create isolated execution environments, ensuring that code runs securely without affecting the host system or other processes. This project is particularly useful for AI applications that require running arbitrary or user-provided code safely. Key features of the project include flexible container management, allowing users to create and manage isolated Docker containers tailored for code execution. It supports custom environments by enabling the use of any Docker image as the execution environment, which provides great flexibility for different programming languages or runtime requirements. The project also facilitates file operations such as transferring files and directories between the host and the containerized environment, making it easy to manage code and dependencies. Users can execute shell commands within the sandboxed containers, with real-time logging support that streams container logs and command outputs live. This feature is essential for monitoring and debugging code execution. The project supports multiple platforms including Linux, macOS, and Windows, making it accessible to a wide range of users. Security is a core aspect of the project, achieved through Docker container isolation and resource limitation features to prevent abuse or resource exhaustion. The project also includes auto-update capabilities to keep the server binary up to date. The project provides a set of tools for initializing sandboxes, copying files or directories, executing commands, stopping containers, and accessing container logs. It integrates with AI applications that support MCP servers, allowing them to use this sandbox as a backend for safe code execution. Overall, "code-sandbox-mcp" is a robust and flexible MCP server solution that enhances the security and manageability of code execution in AI contexts by leveraging containerization technology.
https://github.com/Automata-Labs-team/code-sandbox-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.