url_extract
Any web page → clean, agent-ready text — Pass a URL and get the page as clean text — furniture (nav, scripts, ads, footers) stripped, paragraphs preserved — plus its title, description and site name. The step every agent needs before it can reason about a page, and the one most agents can't do themselves: serverless runtimes and MCP clients have no browser and no HTML parser. Follows redirects safely, refuses non-text content, caps at 2 MB. Nothing crypto about it. Required input: url. Priced $0.002 per call over x402 on Base; send a prepaid x-credit-token header for unlimited calls, or get 1 free call/day per tool. No API key required.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "url_extract"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Page URL | |
| maxChars | No | Max characters (optional) |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| data | No | The result payload. Shape is service-specific; every field is documented in the tool description. | |
| service | No | The service id that answered. | |
| checkedAt | No | ISO-8601 timestamp of when the underlying reads were taken. |