docs: update Browserless MCP description [AUTO-198]

[andyMrtnzP]

No description provided.

[gemini-code-assist]

Code Review

This pull request updates the Browserless MCP documentation to highlight its interactive web agent capabilities, expanding the list of features to include skills, smart scraping, web search, crawling, custom functions, Lighthouse audits, and PDF exports. It also adds a practical example of running the web agent. The feedback suggests improving the grammatical parallelism of the features list by starting each item with an active verb, and updating the new section header to Title Case for consistency.

Important

The consumer version of Gemini Code Assist on GitHub is being sunset. Starting June 18, 2026, new organization installations will be blocked, and all code review activity will officially cease on July 17, 2026.
For more details on the timeline and next steps, please review the Help Documentation.

[gemini-code-assist]

For better readability and adherence to technical writing best practices, use a parallel grammatical structure for all list items. Currently, some items start with active verbs (e.g., 'drive', 'extract', 'follow'), while others start with noun phrases (e.g., 'on-demand recipes', 'structured web', 'performance'). Rewording them to all start with active verbs makes the list much cleaner.

Suggested change

	- **Interactive web agent** — drive a persistent browser session through a multi-step ReAct loop: snapshot the page, plan, click/type/scroll, and re-snapshot. Handles multi-tab workflows, captcha solving, residential proxies, and file upload/download. This is what lets an agent *complete a task on the web* rather than fetch a single page.
	- **Skills** — on-demand recipes the agent loads to handle tricky page mechanics (cookie banners, modals, shadow DOM, dynamic content). They auto-inject when their triggers fire.
	- **Smart scraping** — extract page content as markdown, HTML, or links, with cascading fallback strategies (direct fetch → proxy → headless browser → captcha solving).
	- **Web search** — structured web, news, and image results.
	- **Crawling & site mapping** — follow links to a configurable depth, or discover every URL on a site.
	- **Custom functions** — run arbitrary Puppeteer scripts for complex automation.
	- **Lighthouse audits** — performance, accessibility, best-practices, and SEO scores.
	- **Export & PDF** — capture pages in their native format or as PDFs.
	- **Interactive web agent** — drive a persistent browser session through a multi-step ReAct loop: snapshot the page, plan, click/type/scroll, and re-snapshot. Handles multi-tab workflows, captcha solving, residential proxies, and file upload/download. This is what lets an agent *complete a task on the web* rather than fetch a single page.
	- **Skills** — load on-demand recipes to handle tricky page mechanics (cookie banners, modals, shadow DOM, dynamic content) that auto-inject when their triggers fire.
	- **Smart scraping** — extract page content as markdown, HTML, or links, with cascading fallback strategies (direct fetch → proxy → headless browser → captcha solving).
	- **Web search** — retrieve structured web, news, and image results.
	- **Crawling & site mapping** — follow links to a configurable depth, or discover every URL on a site.
	- **Custom functions** — run arbitrary Puppeteer scripts for complex automation.
	- **Lighthouse audits** — generate performance, accessibility, best-practices, and SEO scores.
	- **Export & PDF** — capture pages in their native format or as PDFs.

[gemini-code-assist]

To maintain consistency with the other section headers in this document (which all use Title Case, e.g., 'Available Capabilities', 'External References'), please update this header to use Title Case as well.

Suggested change

	## 7. Example: running the web agent
	## 7. Example: Running the Web Agent