Webpage Metadata Grounding Data
The tool
Ground agents in live webpage metadata — titles, descriptions and Open Graph tags — so link and content answers reflect the real page, not a guess.
Once your client is connected to the VerveContext MCP server, this appears in its tool list as WebpageMetadataGroundingData. It is read-only and open-world: it fetches, it never mutates anything on your side, so most clients will call it without asking you to confirm.
{
"name": "WebpageMetadataGroundingData",
"arguments": {
"url": "https://www.wikipedia.org"
}
}What that looks like in a conversation
You don't name the tool — the model picks it. Asking about https://www.wikipedia.org in the terms this source covers is enough for it to reach for WebpageMetadataGroundingData on its own.
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"
}
}
}https://api.vervecontext.com/v1/mcpPer-client setup — Claude Desktop, 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.
| Argument | Type | Example | Description |
|---|---|---|---|
urlRequired | string | https://www.wikipedia.org | The URL of the web page to extract metadata from |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client can read fields without parsing prose. status is "ok" on success and error is null; a null field means the value wasn't available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"requestUrl": "https://apiverve.com",
"url": "https://apiverve.com/",
"canonical": "https://apiverve.com",
"lang": "en",
"charset": "utf-8",
"title": "APIVerve - Fast, Scalable, and Reliable APIs",
"image": "",
"favicons": [
{
"rel": "icon",
"type": "image/x-icon",
"href": "/images/favicon.ico"
},
{
"rel": "icon",
"type": "image/png",
"href": "/images/favicon.png"
},
{
"rel": "apple-touch-icon",
"href": "/images/favicon.png"
}
],
"author": "APIVerve",
"description": "APIVerve offers fast, scalable, and reliable APIs for developers. Access data enrichment, validation, and integration services with enterprise-grade performance.",
"keywords": "API, developer tools, data enrichment, API integration, scalable APIs, reliable APIs",
"source": "",
"price": "",
"priceCurrency": "",
"availability": "",
"robots": "index, follow",
"jsonld": [
{
"@context": "https://schema.org",
"@type": "Organization",
"name": "APIVerve",
"url": "https://apiverve.com",
"logo": "https://apiverve.com/images/favicon.png",
"sameAs": [
"https://www.facebook.com/apiverve",
"https://www.twitter.com/apivervehq",
"https://www.linkedin.com/company/apiverve",
"https://github.com/apiverve",
"https://www.instagram.com/apiverve"
]
},
{
"@context": "https://schema.org",
"@type": "WebSite",
"url": "https://apiverve.com",
"potentialAction": {
"@type": "SearchAction",
"target": {
"@type": "EntryPoint",
"urlTemplate": "https://apiverve.com/marketplace?search={search_term_string}"
},Fields
| Field | Type | Example | Description |
|---|---|---|---|
requestUrl | string | Original URL submitted for metadata extraction | |
url | string | Final resolved URL after redirects | |
canonicalPremium | string | Canonical URL from page meta tag | |
lang | string | Page language code from HTML lang attribute | |
charset | string | Character encoding specified in meta tags | |
title | string | Page title extracted from title tag | |
imagePremium | string | Primary image URL from meta tags | |
faviconsPremium | array[3] | Array of favicon objects with URL references | |
└ favicons.0.relPremium | string | ||
└ favicons.0.typePremium | string | ||
└ favicons.0.hrefPremium | string | ||
author | string | Page author extracted from meta tags | |
description | string | Page description from meta description tag | |
keywords | string | Keywords extracted from meta keywords tag | |
sourcePremium | string | Page source or publication reference | |
pricePremium | string | Product price if available in schema | |
priceCurrencyPremium | string | Currency code for price field | |
availabilityPremium | string | Product availability status from schema | |
robots | string | Robots meta tag for search engine indexing | |
jsonldPremium | array[2] | JSON-LD structured data schemas | |
└ jsonld.0.@contextPremium | string | ||
└ jsonld.0.@typePremium | string | ||
└ jsonld.0.namePremium | string | ||
└ jsonld.0.urlPremium | string | Final resolved URL after redirects | |
└ jsonld.0.logoPremium | string | ||
└ jsonld.0.sameAsPremium | array | ||
og:urlPremium | string | Open Graph URL for social media sharing | |
og:localePremium | string | Open Graph locale specification | |
og:locale:alternate | string | ||
og:titlePremium | string | Open Graph title for social sharing | |
og:typePremium | string | Open Graph content type category | |
og:descriptionPremium | string | Open Graph description for social sharing | |
og:determiner | string | ||
og:site_namePremium | string | Open Graph site name for branding | |
og:imagePremium | string | Open Graph image for social media preview | |
og:image:secure_url | string | ||
og:image:type | string | ||
og:image:width | string | ||
og:image:height | string | ||
twitter:titlePremium | string | Twitter card title for X sharing | |
twitter:descriptionPremium | string | Twitter card description for sharing | |
twitter:imagePremium | string | Twitter card image for X preview | |
twitter:image:alt | string | ||
twitter:cardPremium | string | Twitter card type configuration | |
twitter:site | string | ||
twitter:site:id | string | ||
twitter:url | string | ||
twitter:account_id | string | ||
twitter:creator | string | ||
twitter:creator:id | string | ||
twitter:player | string | ||
twitter:player:width | string | ||
twitter:player:height | string | ||
twitter:player:stream | string | ||
twitter:app:name:iphone | string | ||
twitter:app:id:iphone | string | ||
twitter:app:url:iphone | string | ||
twitter:app:name:ipad | string | ||
twitter:app:id:ipad | string | ||
twitter:app:url:ipad | string |
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 with 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 requestUrl: 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 with a sentence the model can act on, not a bare status code.
| Status | What it means |
|---|---|
400 / 422 | The arguments didn't validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Out of credits. Not a bad key — the month's allowance is spent. |
404 | This source isn't part of VerveContext. Check the catalog. |
429 | Brief rate limit. Retrying after a moment succeeds. |
Other ways to use Webpage Metadata Grounding Data
Set up Webpage Metadata 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.
Frequently asked questions
Do I have to tell the agent to use WebpageMetadataGroundingData?
No. The tool's name and description are in the model's context once the server is connected, so it selects the tool when the question calls for it. Naming it explicitly works too and is useful when you want to force the call.
Does connecting the server expose every tool at once?
Yes — one connection lists the whole VerveContext catalog. Clients with a tool budget can usually filter the list; the credit cost is per call, so an unused tool costs nothing.
What does a call cost?
1 credit each time the tool actually runs. A model that reasons about the tool without calling it costs nothing.
Is there a REST version of this?
Yes — the same source is available as a plain HTTPS endpoint on APIVerve, linked above. Same data, same credits, same account.