Trust Onion Scam Check

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Verified AI voice-clone scam incidents, loss stats, and a family verification protocol. Keyless.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Trust Onion Scam Check": {
      "url": "https://trustonion.io/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (7)

• search_incidents read-only

  Search verified, published Trust Onion Pulse (Voice Clone Scam Pulse) incidents by attack type, victim type, country, outcome, incident year, publication date range, and keyword. Returns compact summaries (newest first by default), a total count, and nextCursor for the next page. Call get_incident with a slug for full detail.

  Parameters:

  • sort — string
  • year — integer
  • limit — integer
  • since — string
  • until — string
  • cursor — string
  • country — string
  • keyword — string
  • outcome — string
  • attackType — string
  • victimType — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_incident read-only

  Get the full published Trust Onion case study for one verified incident by slug, including source reporting and prevention analysis.

  Parameters:

  • slug (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_scam_stats read-only

  Return the current Trust Onion Pulse summary (all time, or for one incident year), including conservative loss classifications. Only explicitly-USD losses are summed.

  Parameters:

  • year — integer

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• explain_scam_type read-only

  Explain a documented editorial scam pattern with published article evidence, or a Trust Onion topic hub with warning signs and protection steps. Editorial coverage is not a verified incident count.

  Parameters:

  • scamType (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_scam_types read-only

  List the current editorial scam patterns and published article links, separately from verified incident statistics.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_verification_protocol read-only

  Return Trust Onion's five-step family verification protocol for suspicious calls, texts, and video calls.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• assess_call_scenario read-only

  Deterministically match a described call or text to current scam hubs, red flags, and the recommended verification step. No external LLM is used.

  Parameters:

  • scenario (required) — string

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.