Phishing Threat Grounding Data

Overview

Phishing Domain Checker uses the Phishing.Database project, which aggregates phishing domains from multiple sources, and The Block List Project's phishing list; sources reports which matched. Entries naming a top-50k site outright are excluded so one listed page cannot flag a whole platform. The API accepts either a domain or full URL and checks against the active phishing domains list, and additionally applies list-free structural heuristics — punycode/IDN homograph detection, raw-IP hosts and other indicators — to produce a composite risk score for domains that may not be listed yet.

Live Test Phishing Threat Grounding Data Source →

The tool

Once your client is connected to the VerveContext server, this appears in its tool list as PhishingThreatGroundingData. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.

Tool call

{
  "name": "PhishingThreatGroundingData",
  "arguments": {
    "domain": "centruldepiele.ro"
  }
}

You do not name the tool yourself; the model picks it. Asking about centruldepiele.ro in the terms this source covers is enough for it to reach for PhishingThreatGroundingData on its own — naming it explicitly also works, and is the way to force the call.

Connecting

One server URL covers every source in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.

{
  "mcpServers": {
    "vervecontext": {
      "url": "https://api.vervecontext.com/v1/mcp"
    }
  }
}

Per-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.

Arguments

These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.

Argument	Type	Description
`domain`Required	string	The domain to check (e.g., example.com) domain

What the model gets back

The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.

Result

{
  "status": "ok",
  "error": null,
  "data": {
    "domain": "secure-banking-login.suspicious-domain.com",
    "isPhishing": true,
    "matchedDomain": "suspicious-domain.com",
    "inputType": "url",
    "originalInput": "https://secure-banking-login.suspicious-domain.com/auth",
    "isPunycode": false,
    "isIpAddress": false,
    "riskScore": 85,
    "riskLevel": "high",
    "sources": [
      "phishing-database",
      "blocklistproject"
    ]
  }
}

Response fields

Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.

Field	Type	Example	Description
`domain`	string	`secure-banking-login.suspicious-domain.com`	The domain that was checked for phishing threats
`isPhishing`	boolean	`true`	Whether the domain is a known phishing site
`matchedDomain`Premium	string	`suspicious-domain.com`	The matched phishing domain from threat database
`inputType`	string	`url`	Type of input checked - domain or URL format
`originalInput`	string	`https://secure-banking-login.suspicious-domain.com/auth`	The original input provided by the user
`isPunycode`Premium	boolean	`false`	Whether the domain uses punycode/IDN encoding (xn--), the vector for homograph attacks that impersonate brands with lookalike characters
`isIpAddress`Premium	boolean	`false`	Whether a raw IP address was used in place of a domain, a common trait of malicious links
`riskScore`Premium	number	`85`	Composite 0-100 risk score combining the blocklist match with structural phishing indicators — a heuristic supplement to isPhishing, not a verdict (higher is riskier)
`riskLevel`Premium	string	`high`	Risk band derived from the score: low, medium or high
`sources`Premium	array	`["phishing-database","blocklistproject"]`	Blocklists that matched: phishing-database, blocklistproject; empty when not listed

Why ground on it

A model can produce something that looks like this answer from its training data, and be confidently out of date or simply wrong. This source returns the current value in a shape you can check, which is the difference between an answer you can cite and one you have to hedge.

Point an evaluation at isPhishing: it is the field most worth pinning a claim to, and it is either present and current or absent — never plausibly invented.

Failure modes

Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.

Status	What it means
`400` / `422`	The arguments did not validate. The message names the offending one.
`401`	The OAuth session is invalid or expired — reconnect the server.
`403`	Blocked by a key restriction or an IP allow-list. Never a bad identity.
`404`	This source is not part of VerveContext. Check the catalog.
`429`	Out of credits, or a brief rate limit. The message tells them apart.

A call costs 10 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.

Use cases

Email Security: Check links in emails before users click them to prevent phishing attacks
Browser Extensions: Build security extensions that warn users about phishing sites in real-time
URL Shortener Safety: Verify destination URLs before allowing shortened links to be created
Chat/Messaging Moderation: Automatically detect and block phishing links shared in chat platforms

Other ways to use Phishing Threat Grounding Data

Set up Phishing Threat Grounding Data on VerveContext, or reach the same source a different way. Your VerveContext account and credits work on all of them — one key, one balance.

Call it as a REST APIOne HTTPS endpoint and an x-api-key header, with SDKs for Node, Python and .NET.APIVerve →Reference →

Give it to an AI agentConnect over MCP and your agent calls it as a native tool — Claude, Cursor, ChatGPT.VerveKit →Reference →

Google Sheets or ExcelA =VERVE() formula fills a column — no script, no export, recalculates in place.VerveSheets →Reference →