Clean markdown scraper
clean_markdown_scraperFetch a public web page by URL (or take your HTML) and return Markdown plus headings. No JavaScript rendering. Result carries a signed receipt.
Example tool call
This call uses example arguments supplied in the tool’s input schema.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "https://example.com/"
},
"name": "clean_markdown_scraper"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | No | Public http(s) page to fetch (ports 80/443 only). Provide exactly one of url or html. | |
| html | No | Raw HTML string to convert instead of fetching a URL (max 1 MiB). Provide exactly one of url or html. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| code | No | ||
| tool | No | ||
| scope | No | ||
| valid | No | ||
| reason | No | ||
| source | No | ||
| headings | No | ||
| markdown | Yes | ||
| retryable | No | ||
| wordCount | Yes | ||
| fetched_on | No |