Just describe it

n8n brings Gemini 4 Argon into your workflows

Gemini 4 Argon has just landed in n8n, opening new paths to automation. Some builders now describe what they need in plain language, while others hand whole tasks to agents that decide their own next move. Which approach fits your stack depends on how much control you want to keep.

Oct 14, 2026 | Felipe Santos | Software

n8n is one of the first companies to use and integrate Google's Gemini 4 Argon model. You can use it with your existing n8n workflows or build new ones. The article covers three ways to do this: through MCP, through your own API key with the n8n Assistant, and through an Agent inside a workflow.

Connect through MCP

Model Context Protocol (MCP) is an open standard governed by the Agentic AI Foundation (AAIF). It allows your AI tools to connect to external applications and data sources. n8n has a built-in MCP server that works with any MCP client, so you can build your own workflows from your favourite AI tool. You need access to Gemini 4 Argon in your developer tool and an idea of what you want to build.

Setup takes a couple of minutes. Turn on instance-level MCP in your n8n instance, then add your server URL to any MCP-compatible tool, whether that's a chat app, a coding agent, or an IDE. Many tools support one-click setup and sign in with OAuth or use an API key.

For example, say you're in your IDE building a new signup form, and the webhook is ready. You ask your agent: “Build me an n8n workflow that catches new signups from this webhook, drops them into our CRM, and fires off a welcome message in Slack.” A minute later, the workflow is in your n8n workspace, built and tested. It stops short of publishing and asks first, so you remain the human in the loop.

Bring your own key (BYOK) to the n8n Assistant

The n8n Assistant is a chat-based agent that builds, edits, tests, and debugs workflows from plain language. Bring Your Own Key (BYOK) means the Assistant runs on an AI provider account you already hold, rather than on a model chosen for you. How you set this up depends on where your n8n instance lives.

On self-hosted: You supply the key yourself and decide where your data and model calls go. Drop your key into the instance's settings once, and the Assistant runs on that model. This gives you one account, one model, and one context. The Assistant doesn't have a native Gemini option yet, so you reach Gemini through OpenRouter or through Google's OpenAI-compatible endpoint (base URL: https://generativelanguage.googleapis.com/v1beta/openai/).

On n8n Cloud: There's nothing to set up. The Assistant runs on n8n Assistant credits, and the workflows it builds can use Gemini 4 Argon through Gateway credits.

Build an agent into your workflow

An agent is a model handed a goal and a toolkit. It works out the steps to reach the goal on its own.

In n8n, you set up an agent and use a model such as Gemini 4 Argon for the reasoning. You plug in the tools it's allowed to use, which can be any node, API, or sub-workflow. Optionally, you add memory so it keeps context. From there, the agent decides which tool to call next, loops, and stops when the task is done. Gemini 4 Argon is available as a model for your Agents and in the standalone Google Gemini node from launch. On n8n Cloud, you can also use it through Gateway credits, so you don't need a separate provider account or extra billing. To learn more about how AI agents work in n8n, see https://n8n.io/ai-agents/.

Rigid, step-by-step workflows break down when input gets messy. An agent handles the judgment calls, the surrounding workflow stays predictable, and you still control which tools the agent can reach.

For example, imagine an incoming support email. The agent reads it, pulls the customer record from your CRM, and cross-references your help docs. It then drafts a reply, sets the ticket priority, or drops a flag into Slack for a human to handle.

Wrap up

These are three ways to use the Gemini 4 Argon model in n8n. You can use it through the n8n MCP server to build workflows from inside your favourite AI tool. You can use your own API key with the n8n Assistant to run the latest model alongside you. Or you can use an Agent so the workflow handles judgment calls for you.

Pick the one that works best for you. Happy building.

Takeaways

Connect any MCP-compatible tool to n8n's built-in MCP server to build workflows from your favourite AI tool. Turn on instance-level MCP first, then add the server URL.
On self-hosted n8n, add your own key in the instance settings to run the Assistant on your chosen model. Reach Gemini through OpenRouter or Google's OpenAI-compatible endpoint.
Use an Agent with Gemini 4 Argon for judgment calls, and limit it to the tools it needs.

Source: blog.n8n.io