Modules
| Module | What it does |
|---|---|
| audit | Scans MCP servers for vulnerabilities, maps findings to the OWASP MCP Top 10, outputs SARIF |
| proxy | Intercepts MCP traffic between client and server for inspection, modification, and replay |
| inject | Tests AI agent susceptibility to tool poisoning and prompt injection using configurable payloads |
| chain | Composes multi-step attack sequences across audit findings and inject techniques |
| ipi | Generates adversarial documents with hidden instructions, tracks execution via authenticated callbacks |
| cxp | Builds poisoned instruction files for coding assistants, validates whether models comply |
| rxp | Measures whether adversarial documents win vector similarity battles in RAG retrieval layers |