Enables deterministic security testing of AI agents that use tools by serving synthetic MCP environments with poisoned data, fake secrets, and privileged actions. Records agent tool calls and evaluates security invariants (e.g., canary leaks, forbidden access, approval binding) without an LLM judge or real systems.
Enables hands-on exploration of common MCP security vulnerabilities through locally runnable vulnerable and fixed servers with accompanying exploits and a dashboard.
A controllable, observable MCP server for dynamically setting tools and intercepting calls in real time, useful as a mock/MITM harness for testing MCP clients.
MCP server for security-testing AI models, exposing garak vulnerability scanning and URL/MCP-endpoint scanning as callable tools. It lets agents probe LLM endpoints for jailbreaks, prompt injection, and data leakage, and classify URLs or screen remote MCP endpoints for prompt-injection payloads.
