Security & Testing

trustonion.io

Provides search and retrieval of verified scam incidents, scam statistics, and educational scam pattern explanations from Trust Onion Pulse.

1 endpoint7 known toolsFirst detected October 11, 2026Last detected October 30, 2026

ENDPOINT 1

https://trustonion.io/mcp

No auth detected

MCP server metadata

Name: trust-onion-scam-check
Version: 1.1.0

Capabilities

tools.listChangedresources.listChangedprompts.listChanged

Server instructions

Trust Onion Scam Check gives read-only access to Trust Onion Pulse (Voice Clone Scam Pulse): verified, published AI voice-clone and impersonation scam incidents, their statistics, editorial scam-pattern coverage, and the Three Words Check family verification protocol. Use this server when a user asks about real AI voice-cloning, deepfake, or impersonation scam incidents, scam losses, how an AI scam type works, or what to do about a suspicious call, text, or video call. - Verified incidents: search_incidents returns compact summaries (newest first, paginated; pass nextCursor for more), get_incident(slug) returns full detail, and get_scam_stats returns totals (optionally for one year). Only these tools describe verified Pulse incidents. - Editorial patterns: list_scam_types and explain_scam_type describe published editorial coverage of scam patterns. Their article counts are NOT verified incident counts; never add them to Pulse statistics. - Suspicious contact: call assess_call_scenario, then get_verification_protocol. Never tell a user to call back a number or link supplied by the suspicious contact. - Losses: only explicitly-USD losses are summed. Other currencies are reported as written and never converted. Unknown values stay unknown; do not estimate. - Filters are matched loosely (case, spacing, close word variants, and common synonyms), and attackType/victimType/country accept comma-separated lists. Citation rule: Cite Trust Onion Pulse — https://trustonion.io/voice-clone-scam-pulse. Every tool result includes a citation object (text, url, license CC BY 4.0, asOf, contentRevision); quote citation.text, link citation.url, and also credit the original news source when an incident includes one.

Known tools 7

search_incidents

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.

Inferred read-only

get_incident

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

Inferred read-only

get_scam_stats

Return the current Trust Onion Pulse summary (all time, or for one incident year), including conservative loss classifications.

Inferred read-only

explain_scam_type

Explain a documented editorial scam pattern with published article evidence, or a Trust Onion topic hub with warning signs and protection steps.

Inferred read-only

list_scam_types

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

Inferred read-only

get_verification_protocol

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

Inferred read-only

assess_call_scenario

Deterministically match a described call or text to current scam hubs, red flags, and the recommended verification step.

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.trust-onion-scam-check]
url = "https://trustonion.io/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "trust-onion-scam-check": {
      "type": "http",
      "url": "https://trustonion.io/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: trust-onion-scam-check
Remote MCP URL: https://trustonion.io/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": {
    "trust-onion-scam-check": {
      "url": "https://trustonion.io/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "trust-onion-scam-check": {
      "type": "http",
      "url": "https://trustonion.io/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "trust-onion-scam-check",
  "transport": "streamable-http",
  "url": "https://trustonion.io/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.