AgentDesk MCP
Adversarial AI review API — independent quality gating for AI agent outputs. Provides single and dual reviewer modes with structured verdicts (PASS/FAIL/CONDITIONAL_PASS), scores (0-100), categorized issues, and evidence-based checklists. Built for AI agents that need reliable quality assurance before shipping outputs.
0Tools
0Findings
—Last Scanned
Security Findings0
No findings detected. This server passed all 177 detection rules.
Security Category Deep Dive
Select a category to explore sub-categories, findings, and compliance coverage.