page_to_markdown
Fetch any URL and return clean Markdown. Strips scripts, styles, and HTML tags; preserves headings, links, bold/italic, lists. Useful for reading docs, news, or competitor pages into an LLM context. Deterministic and stateless — no LLM, no API key. 15s timeout, 50KB default output cap.
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": "page_to_markdown"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | http:// or https:// URL to fetch | |
| max_length | No | Max characters to return (content truncated beyond this) |