MCP Service Access — RAG Web Browser
Provides Web browser-based retrieval capabilities via the MCP protocol, utilizing Web page data and model capabilities to process and generate content through combined processing.
Apify RAG Web Browser accepts search phrases or URLs, queries Google Search, then crawls the web pages of the top search results, cleans the HTML, converts it to text or Markdown, and returns it to the LLM for processing. The extracted text can be injected into prompts and retrieval-augmented generation (RAG) pipelines, providing your LLM applications with up-to-date context from the web.
Environment Variables
- Configure APIFY_TOKEN as your API Token on the Apify platform
Usage Instructions
Web Browser RAG MCP Server Reference Documentation
🗺️ Feature List
Tool Identifier | Function Description | Core Parameters |
---|---|---|
search | Query Google Search, crawl the top N URLs from the results, and return their cleaned content in Markdown format | query (search term or url), maxResults (maximum number of search results, default: 1), scrapingTool (select the scraping tool for web page extraction; options: browser-playwright or raw-http, default: raw-http), outputFormats (array of output types: markdown, text, html; example: ['markdown']), requestTimeoutSecs (maximum request time in seconds; default: 40) |
Repository URL
https://github.com/apify/mcp-server-rag-web-browser