Where do I put my Monetzly API key in a n8n app?

In an environment variable (e.g. MONETZLY_API_KEY) read at runtime — never hard-coded in source or shipped to the client.

Do I open a new connection per request in n8n?

Open a connection when a request begins and close it when the response stream finishes. The SDK manages reconnection internally.

How-to guide

How to Set Up the Monetzly SDK in n8n

This guide shows how to set up the Monetzly SDK in a n8n app, the goal being to get the SDK configured and connected before injecting any ads. It builds on the Monetzly server SDK, so the approach is specific to how n8n produces and streams responses.

Overview

Before you can monetize a n8n app, the Monetzly client needs configuring and connecting. This is a one-time setup: an API key, the ad-server address, and SSL settings, then a connection you open when a request starts and close when it ends.

Keep the API key in an environment variable, never in source. Use a non-SSL localhost address in development and your real ad-server host in production.

n8n apps are usually built for automated AI workflows, chatbot backends, and agent orchestration, so set up the Monetzly SDK typically comes up while a user is mid-conversation, the moment where monetization has to be additive rather than disruptive.

How this works on n8n

n8n runs on Node, so a Code node (or a small custom node) can import @monetzly/server-sdk and wrap the token output of an upstream LLM node. Because n8n items are usually discrete rather than a live token stream, confirm whether you inject over a buffered response or a true stream for your workflow.

Because Monetzly's inject() accepts any async token stream, the n8n side of this task is just mapping your output to it, no rewrite of your n8n model call.

Steps

Install the SDK (or, for a Python n8n stack, generate gRPC stubs from the shipped tps_alter.proto).
Create a config with your API key, server address, and SSL flag.
Open a connection at the start of a request and close it when the response finishes.

Integration snippet

// n8n Code node (runOnceForEachItem). TODO_VERIFY: streaming vs buffered output.
import { MonetzlySDK } from "@monetzly/server-sdk";

const sdk = new MonetzlySDK({
  apiKey: $env.MONETZLY_API_KEY,
  serverAddress: $env.MONETZLY_SERVER_ADDRESS,
});
await sdk.connect();

const llmText = $json.text; // output from the previous LLM node
async function* asChunks() { yield { content: llmText }; }

let out = "";
for await (const t of sdk.inject(asChunks(), { prompt: $json.prompt })) out += t.content ?? "";
await sdk.disconnect();
return { json: { text: out } };