Skip to content
Eden Engine
Get started

Web Page Text Extractor (by URL)

omnial/x402-url-to-text

Given a URL, fetches the page with a plain HTTP GET and HTML parse (no JavaScript rendering) and returns its plain-text content, page title, meta description, and detected language. Fast on static/content-heavy pages; a JavaScript-heavy site that renders its content client-side will come back sparse, since no script ever runs.

activeper callv5

Price

Up to $0.0325 per call; you pay what the call used

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $5.00.

Data source

The requested web page

Data from the web page you request.

Use it

Your AI assistant does the work: it finds this tool, shows you the price first, runs it, and you are charged when the run finishes. There is nothing to set up for this tool in particular.

Connect once and your AI can find and run this tool, and any other it needs.

Install itCreate an account
For developers: the calls your assistant makes
agent
// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "omnial/x402-url-to-text" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "omnial/x402-url-to-text" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "omnial/x402-url-to-text", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "omnial/x402-url-to-text", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

ChargePrice
Per call
$0.0325
Updated
Oct 27, 2026

Input and output schemas

Input schema
input_schema.json
{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "description": "URL to extract text from"
    }
  },
  "additionalProperties": false
}
Output schema
output_schema.json
{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The page's plain-text content, HTML tags stripped. Length varies enormously with the source page -- observed as a single short sentence on a minimal static page and as tens of thousands of characters on a long Wikipedia article -- and reflects only what a plain HTTP GET + HTML parse can see: a JavaScript-heavy page that renders its content client-side will shape to a sparse or near-empty string here, since this endpoint never executes JavaScript."
    },
    "title": {
      "type": "string",
      "description": "The page's <title>, e.g. 'Anthropic - Wikipedia', 'Example Domain'."
    },
    "language": {
      "type": [
        "string",
        "null"
      ],
      "description": "Detected page language as a short code, e.g. 'en'. Null when the page declares none."
    },
    "meta_description": {
      "type": [
        "string",
        "null"
      ],
      "description": "The page's <meta name=\"description\"> content, when the page declares one. Often null -- treat this as commonly absent, not guaranteed to be present."
    }
  },
  "description": "The extraction result.",
  "additionalProperties": true
}