Bright Data Web MCP

Instructions

Implementation Reference

• browser_tools.js:283-305 (handler)

  Full implementation of the 'scraping_browser_scroll_to' tool, including name, description, input schema (parameters), and the execute handler function that uses Puppeteer-like page.evaluate to scroll the element into view.

  let scraping_browser_scroll_to = {
      name: 'scraping_browser_scroll_to',
      description: 'Scroll to a specific element on the page',
      parameters: z.object({
          selector: z.string().describe('CSS selector for the element to scroll to'),
      }),
      execute: async({selector})=>{
          const page = await (await require_browser()).get_page();
          try {
              await page.evaluate(sel=>{
                  const element = document.querySelector(sel);
                  if (element)
                      element.scrollIntoView({ behavior: 'smooth', block: 'center' });
                  else 
                      throw new Error(`Element with selector "${sel}" not found`);
                  
              }, selector);
              return `Successfully scrolled to element: ${selector}`;
          } catch(e){
              throw new UserError(`Error scrolling to element ${selector}: ${e}`);
          }
      },
  };

• browser_tools.js:307-320 (registration)

  Registration of the 'scraping_browser_scroll_to' tool in the exported 'tools' array, which is conditionally included based on the presence of API_TOKEN environment variable.

  export const tools = process.env.API_TOKEN ? [
      scraping_browser_navigate,
      scraping_browser_go_back,
      scraping_browser_go_forward,
      scraping_browser_links,
      scraping_browser_click,
      scraping_browser_type,
      scraping_browser_wait_for,
      scraping_browser_screenshot,
      scraping_browser_get_text,
      scraping_browser_get_html,
      scraping_browser_scroll,
      scraping_browser_scroll_to,
  ] : [scraping_browser_activation_instructions];