{
  "name": "hlido-agent-reviews",
  "version": "3.2.0-workers",
  "description": "The trust layer for AI agents — C2PA-verified reviews, Laddoo Scores, queryable over MCP.",
  "transport": [
    "http",
    "streamable-http"
  ],
  "endpoint": "https://hlido.eu/mcp",
  "protocolVersion": "2024-11-05",
  "tools": [
    {
      "name": "trust_check",
      "description": "Hlido trust answer for one agent (slug or URL)."
    },
    {
      "name": "find_trusted",
      "description": "Find Hlido-reviewed agents matching a free-text need."
    },
    {
      "name": "verify_claim",
      "description": "Check whether Hlido's review references a specific claim. Honest nulls when not tested."
    },
    {
      "name": "compare_agents",
      "description": "Side-by-side comparison of up to 5 Hlido-reviewed agents."
    },
    {
      "name": "submit_agent",
      "description": "Submit an AI agent for Hlido review consideration."
    },
    {
      "name": "get_scorecard",
      "description": "Fetch the full sanitized claim-vs-evidence scorecard for one Hlido-reviewed agent. Returns every claim, verdict, evidence quote, source surface, and (for CLI/API tests) the captured command + exit_code + duration. Schema v1.0. Use this for agent-to-agent pre-flight evaluation."
    },
    {
      "name": "get_incidents",
      "description": "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. Filter by agent slug, severity, or category. Use this before delegating to an agent to check for known recent failures; an empty list means no published incidents, not a guarantee of reliability."
    },
    {
      "name": "report_review_issue",
      "description": "Report an issue with a Hlido review (stale info, wrong verdict, missing claim, broken link). Use when calling get_scorecard or trust_check returns data you can prove is incorrect. Hlido's R1 maintenance routine processes reports daily and fires re-tests via dispute-retest sub-agent."
    },
    {
      "name": "request_quick_audit",
      "description": "Request that Hlido audit a NEW AI agent that has no review yet. Use this when trust_check or get_scorecard returns no_review_found and you need a verdict before delegating to the unknown agent. Returns a future scorecard URL + ETA. Free-tier rate-limited (5/day per anonymous, 50/day per identified). The audit produces signed evidence + claim verification within ~24h (sooner if founder triggers manually)."
    },
    {
      "name": "find_similar_agents",
      "description": "Semantic search over Hlido's review corpus. Given a task description (e.g. 'I need an agent that can refactor TypeScript and edit multiple files at once'), returns the top-N reviewed agents ranked by embedding similarity, each with their Laddoo score, evidence_tier, and review URL. Use this when you have a task in mind and want Hlido's recommendation — much better than substring matching via find_trusted."
    },
    {
      "name": "subscribe",
      "description": "Preview — Wave 3 will add persistent webhook + RSS subscriptions. For now this returns the agent's current state plus advisory polling instructions (RSS at /changelog/feed.xml or polling /data/attestations/{slug}.json). Use this to register interest in being notified when a slug's verdict changes."
    },
    {
      "name": "explain",
      "description": "Structured natural-language explanation of why a Hlido-reviewed agent has its current score. Pulls claim-by-claim evidence from the published scorecard. Pass an optional dimension (one of: reliability, transparency, integration, security, evidence) to filter; omit for the full picture. Returns each claim with verdict (PASS|FAIL|PARTIAL|UNKNOWN), a quoted evidence snippet, plus a top-line synthesis."
    },
    {
      "name": "recommend",
      "description": "Constraint-driven recommendation across Hlido's reviewed agents. Pass any combination of: category, min_score, tier, use_case, max_results. Returns ranked candidates each with a why_match line. Use this when you have buyer constraints (budget, category, capability) and want Hlido's filtered shortlist instead of one-by-one trust_check calls."
    },
    {
      "name": "get_behavioral_trace",
      "description": "Fetch the behavioral evaluation trace for a Hlido-reviewed agent — per-task pass/fail, adapter used, behavioral tier, and signed trace link. Returns status 'not_yet_bench_tested' if the slug hasn't been evaluated yet, or 'not_testable' if the agent's interface doesn't support automated bench runs. Use this when you need evidence that an agent's coding/task behaviour has been independently verified beyond marketing claims."
    }
  ],
  "docs": "https://hlido.eu/mcp-docs/",
  "playground": "https://hlido.eu/mcp-docs/playground/",
  "server_card": "https://hlido.eu/.well-known/mcp-server-card/server.json",
  "rest_api": {
    "endpoint": "https://hlido.eu/v1",
    "docs": "https://hlido.eu/api/",
    "openapi": "https://hlido.eu/.well-known/openapi.json"
  },
  "incidents_endpoint": {
    "base_url": "https://hlido.eu/v1/incidents",
    "feed_url": "https://hlido.eu/v1/incidents/feed.xml",
    "submit_url": "https://hlido.eu/incidents/submit",
    "description": "Independent registry of reported AI agent failures. Searchable by slug, severity, date."
  },
  "edge": "cloudflare-workers"
}