reloadium.com

getPageMarkdown

Fetch any public URL and return its content as clean Markdown. Useful for reading articles, documentation, product pages, or any web content the user pastes. The server fetches the page so there are no CORS restrictions. For a YouTube, TikTok, Instagram, or X/Twitter video link, this returns the video's title, author, and full transcript instead of scraping the page — use it directly for "summarize this video" requests rather than a web search. Returns the first 3000 chars; when hasMore is true and the user wants a summary, read the rest with readPageMarkdown (length: 10000) before summarizing — never present a summary of the first chunk as a summary of the whole content.

Page: /

Input schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The full URL to fetch, e.g. https://example.com/article"
    },
    "strictness": {
      "type": "string",
      "enum": [
        "loose",
        "normal",
        "strict"
      ],
      "description": "How aggressively to strip non-article content. Defaults to 'loose'."
    }
  },
  "required": [
    "url"
  ]
}