Back to Templates

Generate a Personal Newsfeed Using Bright Data Web Scraping and GPT-4.1

Created by

Created by: Daniel Shashko || tomax

Daniel Shashko

Last update

Last update 15 days ago

Categories

Share


Personal newsfeed Bright Data MCP  OpenAI.png

How it Works

Disclaimer: This template is for self-hosted n8n instances only.

This workflow is designed for developers, data analysts, and automation enthusiasts seeking to automate personalized news collection and delivery. It seamlessly combines n8n, OpenAI (e.g., GPT-4.1), and Bright Data’s Model Context Protocol (MCP) to collect, extract, and email the latest global news headlines.
On a schedule or via a manual trigger, the workflow prompts an AI agent to gather fresh news. The agent leverages context-aware memory and integrated MCP tools to conduct both search engine queries and direct web page scraping in real time, delivering more than just meta search results—it extracts actual on-page headlines and trusted links. Results are formatted and delivered automatically by email via your SMTP provider, requiring zero manual effort once configured.


Who is this for?

  • Developers, data engineers, or automation pros wanting an AI-powered, fully automated newsfeed
  • Teams needing up-to-date news digests from trusted global sources
  • Anyone self-hosting n8n who wishes to combine advanced LLMs with real-time web data

Setup Steps

  • Setup time: Approx. 15–30 minutes (n8n install, API configuration, node setup)
  • Requirements:
    • Self-hosted n8n instance
    • OpenAI API key
    • Bright Data MCP account credentials
    • SMTP/email provider details
  • Install the community MCP node (n8n-nodes-mcp) for n8n and set up Bright Data MCP access.
  • Configure these nodes:
    • Schedule Trigger: For automated delivery at your chosen interval.
    • Edit Fields: To inject your AI news collection prompt.
    • AI Agent: Connects to OpenAI and MCP, enabled with memory for context.
    • OpenAI Chat Model: Connects via your OpenAI credentials.
    • MCP Clients: Configure at least two—one for search (e.g. search_engine) and one for scraping (e.g. scrape_as_markdown).
    • Send Email: Set up with recipient and SMTP information.
  • Credentials must be entered into their respective nodes for successful execution.

Customization Guidance

  • Prompt Tweaks: Refine your AI news prompt to target specific genres, regions, or sources, or broaden/narrow the coverage as needed.
  • Tool Configuration: Carefully define tool descriptions and parameters in MCP client nodes so the agent can pick the best tool for each step (e.g., only scrape real news sites).
  • Delivery Settings: Adjust email recipient(s) and SMTP details as needed.
  • Workflow Enhancements: Use sticky notes in n8n for extended documentation, alternate prompts, or troubleshooting tips.
  • Run Frequency: Set schedule as needed—from hourly to daily updates.

Once configured, this workflow will automatically gather, extract, and email curated news headlines and links—no manual curation required!