Webpage Metadata

What it grounds

Ground agents in live webpage metadata — titles, descriptions and Open Graph tags — so link and content answers reflect the real page, not a guess.

Ways to ground with it

Ground answers in real data

Enable Webpage Metadata and it becomes a tool your agent calls over MCP to check itself against live data before it answers — grounding the response instead of guessing.

On the same endpoint and key

Webpage Metadata rides the one VerveContext MCP endpoint alongside 300+ other sources, so adding it to an agent is a toggle, not an integration.

Traceable and current

The agent pulls webpage metadata at answer time and can carry the source with the result, so the reasoning stays current and auditable.

Connect over MCP

Point your agent framework at the VerveContext endpoint. Every enabled source — this one included — becomes a tool the model can call. No per-source plumbing.

context.json

{
  "mcpServers": {
    "vervecontext": {
      "url": "https://api.vervecontext.com/v1/mcp",
      "headers": { "x-api-key": "vc_live_••••" }
    }
  }
}

# “metadataextractor” is now a tool your agent can call

Facts your agent can cite

Each call returns structured fields your agent can read — and trace back to this source.

requestUrl
url
canonical
lang
charset
title
image
favicons

Webpage Metadata, answered

How to ground an agent in it over MCP.

How do I give my agent Webpage Metadata?

Enable it on VerveContext and point your agent framework at the VerveContext MCP endpoint. Webpage Metadata then appears to the model as a tool named metadataextractor, which it calls when a task needs it — no per-source plumbing.

Which agents and frameworks can use it?

Any MCP client — Claude, Cursor, LangChain, and custom agents all speak the Model Context Protocol. Webpage Metadata is exposed as a standard tool, so nothing source-specific is required.

Can the agent cite Webpage Metadata?

Yes. Webpage Metadata is verifiable factual grounding — every value the agent pulls can carry Webpage Metadata as its source, so a person (or another system) can trace where the fact came from.

How many credits does a Webpage Metadata call cost?

Each call costs 1 credit. Scoped keys let you grant an agent only the sources it should reach, and usage logs show exactly what was pulled to ground each answer.

How current is the data?

Webpage Metadata is served live from APIVerve's production data engine and pulled at the moment the agent calls it, so answers reflect the world now rather than the model's training cutoff.

Where does the data come from, and what shows on my bill?

VerveContext runs on APIVerve, our production data engine; Webpage Metadata is one of 300+ sources on the same key. Invoices and card statements show APIVERVE.

Ground answers in real data

On the same endpoint and key

Traceable and current

Webpage Metadata, answered

Ground your agents in Webpage Metadata. Connect over MCP, enable the source, and every answer carries its receipts.

Scaling up?