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
flankerhqd/jebmcp
jebmcp is a Model Context Protocol server paired with a plugin script for JEB Pro, the commercial Android and binary reverse engineering suite from PNF Software. It lets an LLM-driven client drive JEB directly, so an agent can decompile an APK, reason about what the code does and write its conclusions back into the project as renamed symbols. The described tool surface includes ping and check_connection for liveness, get_manifest for the Android manifest, get_all_exported_activities together with get_exported_activities_count and get_an_exported_activity_by_index for attack-surface enumeration, get_class_decompiled_code and get_method_decompiled_code for decompilation, get_method_callers and get_method_overrides for call and override relationships, get_superclass, get_interfaces, get_class_methods and get_class_fields for type structure, and rename_class_name, rename_method_name and rename_field_name for renaming. Installation has two parts. The JEB side requires copying src/jeb_mcp/MCP.py into the scripts directory of the JEB installation alongside the Jython file, then starting it from File, Scripts, Scripts selector in the JEB GUI; the logger window should report that the plugin loaded and that a server started on http://127.0.0.1:16161. The client side runs the Python server through uv, with Python 3.11 or newer required, and is registered in the MCP configuration of the client. The repository has been tested with Cline, Cursor and Roo Code, ships a sample_cline_mcp_settings.json, and the README documents a Roo Code walkthrough in Chinese including an mcp.json with autoApprove and alwaysAllow lists for the read-only and rename tools. A demo shows the setup being used to analyse vulnerabilities in an APK. The author describes it as a quick and dirty implementation, modelled on the ida-pro-mcp project.
https://github.com/flankerhqd/jebmcp
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.