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
PortSwigger/mcp-server
The PortSwigger/mcp-server project is a Burp Suite extension designed to implement a Model Context Protocol (MCP) server, facilitating integration between Burp Suite and AI clients. This integration enables advanced AI-driven security testing and automation workflows, enhancing the capabilities of Burp Suite by allowing it to communicate with AI models through the MCP. The extension supports automatic installation for Claude Desktop and includes a packaged Stdio MCP proxy server to accommodate different client requirements. Users can install the extension in Burp Suite, configure the MCP server settings within the extension, and then connect their MCP clients to interact with Burp Suite through the MCP server. The extension listens by default on http://127.0.0.1:9876 and offers configuration options such as enabling the MCP server, allowing tools to edit Burp configuration files, and setting the host and port. The project provides detailed instructions for building the extension using Java and Gradle, loading it into Burp Suite, and configuring it for use with AI clients like Claude Desktop. Claude Desktop clients currently support only STDIO MCP servers, so the extension includes a proxy server that acts as a bridge between the Burp MCP server and the Claude client. Users can either run an installer provided by the extension to configure Claude automatically or manually edit the Claude configuration file to point to the Burp MCP server. Additionally, the project supports manual installation options, including using the SSE MCP server directly or the packaged Stdio MCP proxy server. The source code for the proxy server is available separately, and the extension can extract the proxy server jar for use. Developers can extend the functionality by creating or modifying tools defined in the project, which are serializable data classes that interact with the language model. These tools can support features like auto-pagination and provide rich responses to the language model. Overall, this project is a specialized extension that bridges Burp Suite with AI clients via the Model Context Protocol, enabling sophisticated AI-assisted security testing workflows.
https://github.com/PortSwigger/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.