---
title: "n8n Integration"
description: "Build AI workflows that control your browser"
---

Connect BrowserOS to n8n to build automated workflows. Your n8n AI agents can control the browser—open pages, click buttons, extract data, and fill forms.

## What You Can Build

- **Lead enrichment** — Pull a list of LinkedIn URLs from a spreadsheet and scrape each profile
- **Price monitoring** — Check product prices hourly and send a Slack alert when they drop
- **Form automation** — Auto-fill job applications using data from your CRM
- **Data extraction** — Scrape authenticated pages that require login

## Prerequisites

Before you start:
- BrowserOS running with MCP server enabled (Settings → BrowserOS as MCP)
- n8n running locally (`npx n8n` or install globally with `npm install -g n8n`)

## Setup

### 1. Install the MCP community node

In n8n, go to **Settings → Community Nodes** and install `n8n-nodes-mcp`:

<img src="/images/n8n-node.png" alt="Installing n8n-nodes-mcp community node" />

### 2. Create a workflow

Build a workflow with these nodes:

1. Add a **Chat Trigger** node (receives your messages)
2. Add an **AI Agent** node and connect it to the trigger
3. Add a **Chat Model** under the AI Agent (e.g., OpenAI, Claude)
4. Add an **MCP Client Tool** under the AI Agent

<img src="/images/n8n-step3-workflow.png" alt="n8n workflow with AI Agent and MCP Client" />

### 3. Configure the AI Agent

In the AI Agent node, set **Source for Prompt** to **Connected Chat Trigger Node**.

<img src="/images/n8n-step4-agent-prompt.png" alt="AI Agent prompt configuration" />

### 4. Connect to BrowserOS

Click on the MCP Client node and configure:

- **Endpoint**: Your BrowserOS MCP URL (find it in Settings → BrowserOS as MCP)
- **Server Transport**: `HTTP Streamable`

<img src="/images/n8n-step5-mcp-client.png" alt="MCP Client configuration with BrowserOS URL" />

### 5. Test it

Save the workflow, click **Open chat**, and try:

```
open google.com in BrowserOS
```

<img src="/images/n8n-step6-test.png" alt="Testing the workflow" />

## Troubleshooting

If the connection fails:
- Make sure BrowserOS is running
- Check that MCP server is enabled in BrowserOS settings
- Verify the port number matches your BrowserOS MCP URL