RAG Web Browser (Used in MCP server CI)
Pricing
Pay per usage
Web browser for OpenAI Assistants, RAG pipelines, or AI agents, similar to a web browser in ChatGPT. It queries Google Search, scrapes the top N pages, and returns their content as Markdown for further processing by an LLM. It can also scrape individual URLs. Supports Model Context Protocol (MCP).
Enter Google Search keywords or a URL of a specific web page. The keywords might include the advanced search operators. Examples:
san francisco weatherhttps://www.cnn.comfunction calling site:openai.comThe maximum number of top organic Google Search results whose web pages will be extracted. If query is a URL, then this field is ignored and the Actor only fetches the specific web page.
Select one or more formats to which the target web pages will be extracted and saved in the resulting dataset.
[ "markdown"]The maximum time in seconds available for the request, including querying Google Search and scraping the target web pages. For example, OpenAI allows only 45 seconds for custom actions. If a target page loading and extraction exceeds this timeout, the corresponding page will be skipped in results to ensure at least some results are returned within the timeout. If no page is extracted within the timeout, the whole request fails.
Enables overriding the default Apify Proxy group used for fetching Google Search results.
The maximum number of times the Actor will retry fetching the Google Search results on error. If the last attempt fails, the entire request fails.
Apify Proxy configuration used for scraping the target web pages.
{ "useApifyProxy": true}Select a scraping tool for extracting the target web pages. The Browser tool is more powerful and can handle JavaScript heavy websites, while the Plain HTML tool can't handle JavaScript but is about two times faster.
A CSS selector matching HTML elements that will be removed from the DOM, before converting it to text, Markdown, or saving as HTML. This is useful to skip irrelevant page content. The value must be a valid CSS selector as accepted by the document.querySelectorAll() function.
By default, the Actor removes common navigation elements, headers, footers, modals, scripts, and inline image. You can disable the removal by setting this value to some non-existent CSS selector like dummy_keep_everything.
Specify how to transform the HTML to extract meaningful content without any extra fluff, like navigation or modals. The HTML transformation happens after removing and clicking the DOM elements.
None (default) - Only removes the HTML elements specified via 'Remove HTML elements' option.
Readable text - Extracts the main contents of the webpage, without navigation and other fluff. If readability is not confident or fails, it keeps the original cleaned HTML instead of returning an empty or broken result.
The desired number of web browsers running in parallel. The system automatically scales the number based on the CPU and memory usage. If the initial value is 0, the Actor picks the number automatically based on the available memory.
The maximum number of times the Actor will retry loading the target web page on error. If the last attempt fails, the page will be skipped in the results.
The maximum time in seconds to wait for dynamic page content to load. The Actor considers the web page as fully loaded once this time elapses or when the network becomes idle.
If enabled, the Actor attempts to close or remove cookie consent dialogs to improve the quality of extracted text. Note that this setting increases the latency.