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
ozanunal0/viper
VIPER, short for Vulnerability Intelligence, Prioritization, and Exploitation Reporter, is a Python tool that aggregates vulnerability data and scores it, and ships an MCP server so the same analysis can be driven from an assistant in natural language. It ingests from the National Vulnerability Database, the EPSS exploit prediction scores, the CISA Known Exploited Vulnerabilities catalogue and Microsoft advisories, stores the result in a local database, and applies a weighted multi-factor risk score to rank findings. Language model analysis adds context to each vulnerability; the provider is configurable through the LLM_PROVIDER setting and can be Google Gemini, which is the default, OpenAI, or a local model served by Ollama for analysis that never leaves the machine. Three interfaces exist. A Streamlit dashboard shows the ranked list, per-vulnerability detail, live lookups and trend analytics. A command line entry point processes a window of recent days. The MCP server registers about a dozen cybersecurity tools with clients such as Claude Desktop, including a full live CVE lookup, retrieval of NVD record details, EPSS exploitation probability, a CISA KEV membership check, a search for public exploits on GitHub and Exploit-DB, the model-generated analysis, the computed risk score, and persistence of a record into the local database. Configuring it in Claude Desktop is a single entry pointing at a shell wrapper script in the checkout. Setup is a clone plus a setup script, with credentials and provider choice supplied through a .env file copied from the shipped example. Docker and Docker Compose files are provided, including an Ollama container for the offline configuration. The project targets security analysts and vulnerability management teams who want triage and prioritisation of CVEs without building the data pipeline themselves.
https://github.com/ozanunal0/viper
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.