Tool detail

web-extract

Fetches a public web page and returns its main readable content as clean Markdown or plain text, stripped of navigation and boilerplate.

Categories: Web scraping

Use when

get clean article text from a URL for summarization
extract readable page content for a RAG pipeline

Not for

not for pages requiring login, public URLs only
not a search engine, needs an exact URL

Inputs

GET query params: url (string, required); format (enum markdown|text, optional); render (boolean, optional, headless-browser JS rendering).

Admitted input schema

{
  "type": "object",
  "properties": {
    "format": {
      "type": "string",
      "minLength": 0,
      "maxLength": 4096,
      "enum": [
        "markdown",
        "text"
      ]
    },
    "render": {
      "type": "boolean",
      "description": "Render JS via headless browser"
    },
    "url": {
      "type": "string",
      "minLength": 0,
      "maxLength": 4096,
      "description": "Public http(s) URL to extract"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}

Endpoint

Method: GET
URL: https://api.agentstools.dev/extract

Payment

Protocol: x402
Listed price: $0.002 USDC per call on Base
Payment method: exact
Network: eip155:8453
Asset: 0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913

Listed terms are catalog metadata. The caller supplies inputs and calls the tool outside Onelayer. If payment is required, the caller uses a compatible wallet to pay.

Source

Directory: Coinbase x402 Bazaar
Record: GET https://api.agentstools.dev/extract
Retrieved: 2026-09-30T20:37:07.382Z
Catalog file SHA-256: 6837ccddf886f0007cf3727ea9d27faaa5047b51b4f425345c554ce1c271a524
Catalog built: 2026-09-30T22:31:58.034Z