Awesome AI Agents › Runtime Analysis Tools
MCP Scanner is a Python security tool from Cisco AI Defense that audits Model Context Protocol servers and the tools they expose for signs of malicious or unsafe behavior. It combines three scanning engines that can be enabled together or independently: YARA pattern rules, an LLM-as-a-judge analysis pass, and the hosted Cisco AI Defense inspect API. The scanner covers the full surface of an MCP server, checking tool definitions, prompts, resources and server instructions, and it can also read the server source code for behavioral threats such as prompt injection hidden in tool descriptions. Beyond the protocol layer it audits the supply chain around a server: Python dependencies are checked against CVE, PYSEC and GHSA advisories through pip-audit, binary files bundled with a server such as images, PDFs, executables and archives are looked up by hash in VirusTotal, and PyPI packages can be downloaded and run through behavioral analysis inside a Docker sandbox. A separate readiness scan performs zero-dependency static analysis for production concerns like missing timeouts, retries and error handling. The tool runs either as a standalone CLI or as a REST API server, and it can operate in static mode against pre-generated JSON descriptions of a server, which suits CI/CD pipelines and air-gapped environments where a live connection is not possible. Authentication is explicit rather than implicit, with fine-grained Auth parameters and full OAuth support for both SSE and streamable HTTP transports, and the API endpoint is configurable for different Cisco AI Defense environments. Users can add their own YARA rules to catch organization-specific patterns, and scans produce detailed reports of findings. The project requires Python 3.11 or newer, is installed from PyPI as cisco-ai-mcp-scanner, and is Apache-2.0 licensed. It targets security teams securing an agent tool supply chain.
https://github.com/cisco-ai-defense/mcp-scanner
PrivateGPT is a fully private, offline-capable AI platform that enables users to interact with their documents using Large Language Models through a comprehensive API and user-friendly interface, ensuring data never leaves the user's environment.
PentAGI is a fully autonomous AI-driven penetration testing system that integrates professional security tools, multi-agent AI collaboration, and scalable microservices architecture to deliver comprehensive and automated security assessments.
Impacket is a Python library offering low-level programmatic access and implementations for various network protocols, focusing on security research and educational use.
VIPER is a versatile and powerful red team platform that supports adversary simulation and cybersecurity assessments across multiple operating systems, enhanced with AI-driven automation and extensive post-exploitation capabilities.
MCP-Scan is a security tool that statically and dynamically scans MCP connections to detect and prevent vulnerabilities like prompt injections, tool poisoning, and cross-origin escalations, offering real-time monitoring and customizable guardrails for enhanced protection.
OpenRecall is a fully open-source, privacy-focused digital memory tool that captures and makes searchable your digital history through screenshots, supporting Windows, macOS, and Linux with local data storage and advanced semantic search capabilities.
MCP server that exposes Cheat Engine memory reading, scanning, disassembly and debugging to AI agent clients through roughly 180 tools over a named pipe or TCP relay.
Amon is a modern, open-source server monitoring platform designed to help users track and manage server performance and uptime effectively.