fetch_content
Read one or more URLs and convert them to clean markdown. Renders pages in a real browser to capture JavaScript-heavy content, fetching up to 10 URLs in parallel.
Instructions
Read one or more URLs and return clean markdown. Free. Renders in a real browser, so JavaScript-heavy pages work. Up to 10 URLs, fetched in parallel. Prefer this over curl or raw HTTP for page content.
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": {
"urls": "<urls>"
},
"name": "fetch_content"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| ttl | No | Cache tolerance in seconds. 0 forces a live fetch. | |
| urls | Yes | 1-10 http(s) URLs. | |
| links | No | Also return outbound URLs. | |
| format | No | Defaults to markdown. | |
| purpose | No | Why you are fetching; tailors extraction. | |
| exclude_selectors | No | CSS selectors to strip, e.g. [".comments"]. | |
| include_selectors | No | CSS selectors to scope extraction to, e.g. ["main"]. |