Docs/Sources/URL Unshortening Grounding Data

URL Unshortening Grounding Data

Unshorten Shortened URLs

OperationalCredits 10 per callp50 1550msDomain Data

Overview

URL Unshortener works by following the shortened URL's HTTP redirects to its final destination. It returns the resolved URL, the destination domain, the number of redirect hops, and the full hop-by-hop redirect chain — so you can see exactly where a link goes and which intermediate domains it passes through before trusting it.

Live Test URL Unshortening Grounding Data Source →

The tool

Once your client is connected to the VerveContext server, this appears in its tool list as URLUnshorteningGroundingData. 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": "URLUnshorteningGroundingData",
  "arguments": {
    "url": "https://bit.ly/3k3j4"
  }
}

You do not name the tool yourself; the model picks it. Asking about https://bit.ly/3k3j4 in the terms this source covers is enough for it to reach for URLUnshorteningGroundingData 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.

ArgumentTypeDescription
urlRequiredstringThe shortened URL to unshorten
url

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": {
    "source": "https://bit.ly/3k3j4",
    "destination": "http://www.allclimbing.com/archive/2009/09/climbing-video-alex-puccio-on-trice-v12/",
    "unshortened": true,
    "redirectCount": 1,
    "destinationDomain": "www.allclimbing.com",
    "redirectChain": [
      "https://bit.ly/3k3j4",
      "http://www.allclimbing.com/archive/2009/09/climbing-video-alex-puccio-on-trice-v12/"
    ]
  }
}

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.

FieldTypeExampleDescription
sourcestringhttps://bit.ly/3k3j4The shortened URL that was provided as input
destinationstringhttp://www.allclimbing.com/archive/2009/09/climbing-video-alex-puccio-on-trice-v12/The original unshortened URL destination
unshortenedbooleantrueWhether the URL was successfully unshortened
redirectCountnumber1Number of HTTP redirect hops followed from the source to the final destination (0 if the URL was already final)
destinationDomainstringwww.allclimbing.comHostname of the final resolved destination URL
redirectChainPremiumarray["https://bit.ly/3k3j4","http://www.allclimbing.com/archive/2009/09/climbing-video-alex-puccio-on-trice-v12/"]Ordered list of every URL visited, starting with the source and ending at the final destination — the intermediate entries are the redirect hops (tracking or cloaking domains) the link passes through

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 source: 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.

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

Malicious Link Screening
Screen user-submitted short links in messaging platforms by resolving them to their final destination domain before security filters evaluate the URL.
Social Media Moderation
When forum commenters post shortened URLs, resolve the link destination to flag forbidden affiliate networks or banned domains.
Email Gateway Scanning
Corporate mail scanners check incoming emails for shortened links, inspecting the resolved destination URL and redirect count to detect evasion tactics.
Affiliate Link Auditing
Verify affiliate campaign redirects across ad networks by extracting the destination domain and confirming whether tracking links reach active target sites.

Other ways to use URL Unshortening Grounding Data

Set up URL Unshortening 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 →

More in Domain Data:

Was this page helpful?