Fetch page as Markdown
fetch_pageDownload a web page as clean Markdown with its main content and metadata, enabling reliable reading, summarization, quoting and fact-checking of a specific URL.
Instructions
Download a web page and return its main readable content as clean Markdown (navigation, ads, scripts and boilerplate removed, links made absolute) plus title, meta description, language, canonical URL and word count. Use this whenever you need to read, summarise, quote or fact-check a specific URL. mode "article" (default) uses Mozilla Readability for articles/blog posts/docs; use mode "full" for home pages, landing pages or listings where the article detector would drop content. Output is truncated to max_chars.
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_page"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Absolute http(s) URL. A bare domain like example.com is treated as https://example.com. | |
| mode | No | "article" = main article only (Readability); "full" = the whole <main>/<body> minus header/nav/footer. | article |
| max_chars | No | Maximum Markdown characters to return. Lower it to save context; raise it for long documents. | |
| include_links | No | Also return up to 100 links found on the page. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| lang | Yes | ||
| bytes | Yes | ||
| links | No | ||
| title | Yes | ||
| byline | Yes | ||
| status | Yes | ||
| finalUrl | Yes | ||
| markdown | Yes | ||
| siteName | Yes | ||
| canonical | Yes | ||
| elapsedMs | Yes | ||
| extractor | Yes | ||
| fromCache | Yes | ||
| openGraph | Yes | ||
| truncated | Yes | ||
| wordCount | Yes | ||
| description | Yes | ||
| publishedTime | Yes |