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
tuananh/hyper-mcp
hyper-mcp is a high-performance, secure Model Context Protocol (MCP) server designed to extend AI capabilities through the use of WebAssembly plugins. It supports a wide range of deployment environments including cloud, edge, mobile, and IoT devices, making it versatile for various application needs. The server is compatible with MCP-enabled applications such as Claude Desktop and Cursor IDE, allowing seamless integration and enhanced AI functionality. The core strength of hyper-mcp lies in its ability to run plugins written in any language that compiles to WebAssembly, distributed via standard OCI registries like Docker Hub. This flexibility enables developers to write and deploy AI extensions easily and securely. The server is built on the Extism framework, which ensures robust plugin support and sandboxed execution, preventing unauthorized system access and enforcing memory safety with resource limits. hyper-mcp supports all three protocols defined in the MCP specification: stdio, SSE, and streamable HTTP, providing multiple communication options for different use cases. Security is a primary focus, with features such as signed OCI plugin images verified at load time using sigstore, fine-grained access control for host functions, and secure plugin distribution. These measures ensure that plugins operate safely within controlled environments. The project includes a variety of example plugins covering functionalities like time calculations, QR code generation, hashing, IP retrieval, web fetching, cryptocurrency prices, file system operations, and more. It also supports community-built plugins, expanding its ecosystem further. Developers can create and publish their own plugins following provided examples and Docker-based build instructions. Overall, hyper-mcp is a powerful, secure, and flexible MCP server that facilitates the extension of AI capabilities through WebAssembly plugins, suitable for diverse deployment scenarios and emphasizing security and ease of use.
https://github.com/tuananh/hyper-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.