Documentation

Guides, references, and tutorials for all Cisco AI Defense open-source security tools.

DefenseClaw

Enterprise governance for AI agents — scan, enforce, and audit every skill, MCP server, and plugin before it runs.

VS Code extension for scanning MCP servers, agent skills, and generating secure AI code with CodeGuard.

Security scanner for AI agent skills. Detects malicious behaviors, hidden instructions, and vulnerable patterns.

Scan Model Context Protocol (MCP) servers for potential threats, security findings, and malicious tool behaviors.

Scan Agent-to-Agent communication and behaviors for potential threats and security issues.

Generate AI Bill of Materials through automated source code scanning and dependency analysis.

Official Python SDK for integrating with the Cisco AI Defense enterprise platform.

Domain-adapted language model for cybersecurity intelligence — semantic search, NER, and threat analysis.

Structure-aware test case generator for Python pickle parsers and validators.

Infrastructure templates for deploying Cisco AI Defense hybrid on AWS EKS.