How to Use Llama 4 for FREE in n8n with Perplexity MCP
Leonardo Grigorio | Build & Ship with AI
@leonardogrigAbout
Your idea deserves to exist. I help builders at any level ship production data-driven apps using AI, modern tools, and a bias toward action.
Video Description
🔥 Join The AI Forge Community 👇 https://www.skool.com/the-ai-forge In this video, I evaluate the new Llama 4 Scout model, accessed for free via Groq, and integrate it within n8n to use Perplexity's MCP tool for real-time AI news searches. I compare Llama 4's performance, speed, and cost-effectiveness against Claude 3.5 Sonnet for the same task, noting differences in how they utilize the search tool. I walk you through the simple steps to get your Groq API key, set up Llama 4 Scout in your n8n workflow, and then configure the Perplexity MCP 'list tools' and 'execute tool' functions, ensuring the AI agent can effectively leverage external search capabilities for up-to-date information. Timestamps: 00:00 - Intro: Llama 4 + Perplexity Demo 01:02 - Comparing Llama 4 vs Claude 3.5 for Tool Use 02:11 - Setting up Llama 4 Scout (Free via Groq) in n8n 03:14 - Adding & Configuring Perplexity MCP Tool in n8n 05:48 - Final Test & Results ✨n8n Cloud (Affiliate Link—Using it supports me!): https://n8n.partnerlinks.io/c2uubbc6vgax 🔥 Scrape with Firecrawl : https://firecrawl.link/leo The Recording Software I use (Canvid): https://aibuilders.short.gy/canvid 📱 X: https://x.com/leonardogrig 💼 LinkedIn: https://www.linkedin.com/in/leonardogrig
Essentials for AI Automation Enthusiasts
AI-recommended products based on this video

Seasonic Focus V4 GX-1000 (ATX3) - 1000W - 80+ Gold - ATX 3.0 & PCIe 5.1 Ready -Full-Modular -ATX Form Factor -Premium Japanese Capacitor -10 Year Warranty -Nvidia RTX 30/40 Super & AMD GPU Compatible

PNY NVIDIA Quadro RTX 4000 - The World’S First Ray Tracing GPU

















