Implementation of an MCP server for the RAG Web Browser Actor. This Actor serves as a web browser for large language models (LLMs) and RAG pipelines, similar to a web search in ChatGPT.
Query Google Search, scrape the top N URLs from the results, and returns their cleaned content as Markdown. Arguments: query (string, required), maxResults (number, optional), scrapingTool (string, optional), outputFormats (array, optional), requestTimeoutSecs (number, optional)
No reviews yet. Be the first to review!
Sign in to join the conversation
After downloading, you can run the MCP server in any client or IDE:
node path/to/downloaded/file.mjs