93Trusted

ezark-consulting/agentdesk-mcp

Trusted
Share

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.

AgentDesk MCP
smithery

Security Findings

No security issues found

This server passed all security checks.

Score Breakdown

Code Analysis100/100 (30%)
Dependency Health100/100 (20%)
Permission Safety100/100 (20%)
Behavioral Stability85/100 (15%)
Transparency70/100 (15%)

Server Info

Trust Level
trusted
Source
smithery
Last Scanned
3/31/2026

Report an Issue

Found something suspicious? Help the community by reporting it.