web_fetch
Fetch the plain-text content of any public web page, with HTML stripped and no browser needed. Use it to read articles, docs, or any URL.
Instructions
Fetch the plain-text content of any public web page. HTML is stripped. No browser needed, no permission required. Use this to read articles, docs, pricing pages, or any URL the user mentions.
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": "web_fetch"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Full URL to fetch (https:// assumed if omitted). | |
| max_chars | No | Max characters of plain text to return (500–32000). |