MCP server that detects and guards against tool poisoning and prompt injection attacks in tool descriptions and schemas. It provides risk scoring, pattern detection, safe rewriting, and audit reports with zero external API cost.
MCP server that scores tool descriptions, estimates token costs, simulates agent tool selection, and generates reliability reports to help AI agents choose the right tools and reduce wasted tokens.
Provides audit_plugin_health and prepare_semantic_review tools for deterministic inspection of Codex plugins and Agent Skills, generating evidence-backed reports without executing or transmitting target code.
Wraps three deterministic audit scripts (funnel, accessibility, LLM visibility) as MCP tools, returning honest markdown reports with no fabricated results.
Agent-native Amazon catalog auditing tool that enables AI agents to scan, check, and diff Category Listing Reports and live Seller Central listings via MCP tools.
