Enables deterministic security testing of AI agents that use tools by serving synthetic MCP environments with poisoned …
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.
ofirtro
mcp
free
No benchmark results have been added yet.