Glasser
← Serper

Provided by Serper

Fetch the Readable Content of One Web Page by URL (Serper)

$0.0022 per callanswers within 20s

Fetch one web page by its URL and get the readable content Serper extracts from it, an optional Markdown version and the page metadata. Supply an http or https URL, plus the includeMarkdown flag when you want Markdown as well. One page per call, and a page whose body comes back empty counts as no result.

Contract snapshot: 2026-09-29. Inspect in Glasser for current terms.

json
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "pattern": "^https?:\\/\\/.+"
    },
    "includeMarkdown": {
      "type": "boolean"
    }
  },
  "additionalProperties": false
}

How to run it

Two fields identify it: the Provider and the endpoint key. The key looks like a path because it usually mirrors the Provider's own, but it is an opaque identifier — not a URL you can open. The same provider:endpoint pair is what your Policy lists.

Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.

Setup prompt
set up https://glasser.ai/SKILL.md

Then ask for this Endpoint:

Agent prompt
Run the Serper Endpoint /scrape on Glasser with input {"url":"https://example.com","includeMarkdown":true}

What each outcome charges

No resultThe Provider answered: nothing matched.$0.0022
Provider errorThe Provider failed to answer.$0.00
Timed outThe deadline won.$0.00
Internal failureOur defect.$0.00
Method POSTVersion 3Provider documentation ↗