Read a web page as Markdown
read_urlFetch a public web page and convert its main content into clean Markdown, excluding navigation, scripts, and ads, while respecting robots.txt and returning the page title and description.
Instructions
Fetch a public web page and return its main content as clean Markdown (no navigation, scripts or ads), with title and description. Respects robots.txt and refuses private/internal addresses. Runs locally; maxChars defaults to 50,000 (max 200,000).
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": "read_url"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Absolute http(s) URL | |
| maxChars | No | Maximum Markdown characters to return (default 50000) |