Web Browser

Scrape a web page via Firecrawl. Runs on the backend MCP server, no sandbox needed. Pass formats to choose what comes back: - markdown (default): clean LLM-ready text - html / rawHtml: cleaned vs. unmodified - images: array of image URLs on the page - links: array of hyperlink U…

मूल्य

मुफ़्त Action

एकीकृत भुगतान

अभी समर्थित नहीं

• urlstring

  आवश्यक
  Page URL to scrape
• querystring
  Natural-language structured-extraction prompt
• execJsstring
  JavaScript to run before extraction
• schema
  JSON schema for structured extraction
• actionsarray
  Raw Firecrawl actions JSON (scroll/click/wait/executeJavascript/screenshot)
• countrystring
  Geo-proxy country code, e.g. 'US'
• formatsarray
  Formats to return: markdown, html, rawHtml, images, links, branding, summary, screenshot. Default ['markdown'].
• timeoutinteger
• waitForinteger
  ms to wait for page load before extraction
• fullPageboolean
  Capture the full scrollable page (screenshot format)
• projectIdstring
  Existing project ID from the editor URL or list_projects. Pass this when continuing work on an existing project and the external MCP session is not already targeted.
• onlyMainContentboolean
  Strip nav/footer/ads

कोई समीक्षित संरचित आउटपुट सारांश उपलब्ध नहीं है।

अभी कोई सत्यापित संबंधित उपयोग मामला लिंक नहीं है।