AI & Machine Learning

hlido.eu

Provides tools to check, compare, and verify the trustworthiness and claims of AI agents based on independent testing.

1 endpoint19 known toolsFirst detected May 10, 2026Last detected September 6, 2026

ENDPOINT 1

https://hlido.eu/mcp

No auth detected

MCP server metadata

Name: hlido-agent-reviews
Version: 3.3.0-workers

Capabilities

tools

Known tools 19

trust_check

The core Hlido trust query: is a specific AI agent trustworthy?

Inferred read-only

find_trusted

Discover Hlido-reviewed agents that match a free-text need, ranked by trust.

Inferred read-only

verify_claim

Fact-check one specific marketing or capability claim about an agent against Hlido's independent testing.

Inferred read-only

compare_agents

Head-to-head trust comparison of 2-5 Hlido-reviewed agents.

Inferred read-only

submit_agent

Nominate a new AI agent for Hlido to review.

Inferred read-only

verify_transparency

Check any AI agent's EU AI Act Article-50 transparency posture — including agents Hlido has NOT reviewed yet.

Inferred read-only

get_scorecard

Fetch the full sanitized claim-vs-evidence scorecard for one Hlido-reviewed agent.

Inferred read-only

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.

Inferred read-only

report_review_issue

Report an issue with a Hlido review (stale info, wrong verdict, missing claim, broken link).

Inferred read-only

request_quick_audit

Request that Hlido audit a NEW AI agent that has no review yet.

Inferred read-only

find_similar_agents

Semantic search over Hlido's review corpus.

Inferred read-only

subscribe

Preview — Wave 3 will add persistent webhook + RSS subscriptions.

Inferred read-only

explain

Structured natural-language explanation of why a Hlido-reviewed agent has its current score.

Inferred read-only

recommend

Constraint-driven recommendation across Hlido's reviewed agents.

Inferred read-only

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.

Inferred read-only

commerce_check

Check whether a Hlido-reviewed agent is ready to be delegated to / transacted with in the agentic-commerce world (MCP/ACP/AP2).

Inferred read-only

scan_mcp

On-demand independent SAFETY scan of an MCP server — call this BEFORE installing or connecting to one.

Inferred read-only

market_pulse

Fetch the Agent Market Pulse — machine-readable market intelligence for the AI-agent market, derived from Hlido's independently tested corpus (never vendor self-reports): tier-health distribution, per-category health, new-entrant rate, public-surface readiness, EU AI Act Article-50 compliance bands, and the not-testable mortality signal.

Inferred read-only

intel_query

Query Hlido's market-intelligence store: durable, evidence-cited claims about the AI-agent market and adjacent domains (agent economy, payments rails, EU compliance), each with dated evidence, confidence, and typed relations to other intel.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.hlido-agent-reviews]
url = "https://hlido.eu/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "hlido-agent-reviews": {
      "type": "http",
      "url": "https://hlido.eu/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: hlido-agent-reviews
Remote MCP URL: https://hlido.eu/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "hlido-agent-reviews": {
      "url": "https://hlido.eu/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "hlido-agent-reviews": {
      "type": "http",
      "url": "https://hlido.eu/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "hlido-agent-reviews",
  "transport": "streamable-http",
  "url": "https://hlido.eu/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.