fetch_url_content
Fetches webpage main content and converts it to Markdown by removing navigation and ads, with caching and headless-browser fallback for JavaScript pages.
Instructions
抓取网页正文并转为 Markdown(自动去导航/广告,处理中文编码)。
5 分钟内重复抓取同一 URL 直接命中缓存。发生重定向时结尾标注最终 URL。
Args: url: 目标网址(http/https)。 max_chars: 返回正文最大字符数,默认 20000,超出截断并标注。 render_mode: "auto"(默认,HTTP 优先、失败时无头浏览器兜底)/ "request"(强制纯 HTTP,最快,不启动浏览器)/ "browser"(强制无头浏览器渲染,已知是 JS 页面时用,省一次无效 HTTP)。
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": "fetch_url_content"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| max_chars | No | ||
| render_mode | No | auto |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |