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
SimonB97/win-cli-mcp-server
The project "win-cli-mcp-server" by SimonB97 is a Model Context Protocol (MCP) server designed specifically for Windows environments. It facilitates secure and controlled command-line interactions across multiple shell environments including PowerShell, Command Prompt (CMD), and Git Bash. Additionally, it supports remote command execution on systems via SSH, enabling comprehensive remote management capabilities. The server is intended to be used with MCP clients such as Claude Desktop, allowing these clients to perform system operations securely and efficiently. Key features of the server include multi-shell support, SSH support for remote systems, and exposure of resources like SSH connections, current directories, and configuration details as MCP resources. The server emphasizes security with extensive controls such as command and SSH command blocking, working directory validation, maximum command length limits, command logging, history tracking, and smart argument validation. These features ensure that only authorized commands and operations are executed, minimizing security risks. The server is highly configurable through a JSON configuration file that allows users to define security rules, shell-specific settings, SSH connection profiles, path restrictions, and blocked command lists. The default configuration is restrictive and secure, blocking potentially dangerous commands and arguments, restricting command execution to allowed directories, and enabling injection protection. Users can customize these settings to fit their security requirements and operational needs. The project also provides detailed documentation on usage, configuration, and security considerations. It includes instructions for integration with Claude Desktop and guidance on creating and managing configuration files. Despite its powerful capabilities, the project notes that development has stalled and recommends a more mature alternative for users seeking ongoing support. Overall, this MCP server project offers a robust solution for secure, multi-shell command-line management on Windows systems with strong security and configurability features, making it suitable for users needing controlled and auditable command execution environments.
https://github.com/SimonB97/win-cli-mcp-server
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.