This tool is no longer present in the server's latest manifest. Showing the last observed version (server version 1.0.0).
web_extract
InactiveTool of io.sslip.195.82.231.168/agent-data-api
declared in 1.0.0
Extract clean, readable content from a messy HTML page (one URL). Returns title, byline, meta description, the main article text (boilerplate/nav/ads stripped, up to ~12k chars), a word count, and the main in-content links. Ideal for feeding a page to an LLM without the chrome.
Parameters schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "http(s) URL of the page to extract"
},
"_x402Payment": {
"type": "string",
"description": "OPTIONAL base64 x402 payment (USDC/Base). Only needed when the tool returns a -32402 payment-required error."
}
},
"additionalProperties": false
}No endpoints wrapped at confidence ≥ 0.50.
Parent server
io.sslip.195.82.231.168/agent-data-api
1/7 registries