Hlido

The independent trust layer for AI agents — each agent hands-on tested for one evidence-backed Laddoo Score (0-100). Query trust checks, scorecards, incidents, and recommendations over MCP.

Skills

• trust check
  The core Hlido trust query: is a specific AI agent trustworthy? Given one agent (by Hlido slug or product/homepage URL) it returns the independent Laddoo trust score (0-100), tier (VITAL/STEADY/FADING/FLATLINE), a one-line verdict, a claim-verification summary, and any known incidents.
  trustai-agentsevaluation
• find trusted
  Discover Hlido-reviewed agents that match a free-text need, ranked by trust.
  trustai-agentsevaluation
• verify claim
  Fact-check one specific marketing or capability claim about an agent against Hlido's independent testing.
  trustai-agentsevaluation
• compare agents
  Head-to-head trust comparison of 2-5 Hlido-reviewed agents.
  trustai-agentsevaluation
• submit agent
  Nominate a new AI agent for Hlido to review.
  trustai-agentsevaluation
• get scorecard
  Fetch the full sanitized claim-vs-evidence scorecard for one Hlido-reviewed agent.
  trustai-agentsevaluation
• get incidents
  Fetch published incidents from Hlido's NTSB-style failure registry — real observed agent failures (availability outages, regressions, hallucinations, safety issues) plus Hlido self-reported process incidents, each with severity, evidence, and vendor-response status.
  trustai-agentsevaluation
• report review issue
  Report an issue with a Hlido review (stale info, wrong verdict, missing claim, broken link).
  trustai-agentsevaluation
• request quick audit
  Request that Hlido audit a NEW AI agent that has no review yet.
  trustai-agentsevaluation
• find similar agents
  Semantic search over Hlido's review corpus.
  trustai-agentsevaluation
• subscribe
  Preview — Wave 3 will add persistent webhook + RSS subscriptions.
  trustai-agentsevaluation
• explain
  Structured natural-language explanation of why a Hlido-reviewed agent has its current score.
  trustai-agentsevaluation
• recommend
  Constraint-driven recommendation across Hlido's reviewed agents.
  trustai-agentsevaluation
• get behavioral trace
  Fetch the behavioral evaluation trace for a Hlido-reviewed agent — per-task pass/fail, adapter used, behavioral tier, and signed trace link.
  trustai-agentsevaluation
• commerce check
  Check whether a Hlido-reviewed agent is ready to be delegated to / transacted with in the agentic-commerce world (MCP/ACP/AP2).
  trustai-agentsevaluation
• scan mcp
  On-demand independent SAFETY scan of an MCP server — call this BEFORE installing or connecting to one.
  trustai-agentsevaluation

How to call

https://hlido.eu/mcp