See llms.txt for all machine-readable content.

Build + update n8n workflows from inside your AI app

No more copy-paste. Simply tell Claude, ChatGPT, or your IDE what you want to build, and get a ready-to-run workflow in minutes — built directly in n8n.

*Get started by enabling MCP

Over 200k Github stars

Self host-able

SOC2 compliant

AI agents and workflows for technical teams at

Building workflows with AI used to be copy, paste...and pray

  • JSON files that fail

    You copy-paste workflow JSON that AI created into n8n. It breaks. Deprecated options. Missing parameters. Hallucinations. A mess.

  • AI blindness to what breaks

    AI makes a small edit — and something else breaks. With no way to see the live workflow state, AI can’t verify its changes. “I need to rewrite the SDK” isn’t what you signed up for.

  • Debugging in the dark

    Without access to workflow logs, figuring out why they failed becomes a forever loop. You give AI the error messages, manually apply the changes, and re-run—until you give up.

Now you can go right from prompt to ready-to-run flow

The n8n MCP server connects your n8n instance to any AI app or IDE that speaks MCP. So you can build, edit, and test workflows inside n8n with AI, using natural language alone.

Included on all n8n plans

Maintained by n8n

No 3rd parties

Workflows that work, in a matter of minutes

Once you’ve connected your AI MCP client to n8n, simply tell it what you want to build. It will create the workflow, validate it, and fix it all by itself if it breaks.

Works with the AI you already use

Claude, ChatGPT, Gemini, or Cursor. If your AI supports MCP — and they basically all do — you can build workflows with them directly inside n8n. Endless copy-paste is a thing of the past.

Fix workflows without switching tabs

Live access to your n8n instance allows AI apps to understand, audit, and improve your workflows. So when a workflow fails, your AI reads the actual execution logs — and fixes the bug. No tab dancing necessary.

Use n8n best practices to build better workflows

Add n8n’s official skills to your AI app, and it reviews them before starting to build. So it takes AI less time — and costs you fewer tokens — to get it right.

Check out the n8n Skills GitHub repo →

How to connect your AI app to n8n

First, enable MCP in your n8n instance. Then, add the MCP server to your AI app.
The exact process for connecting each AI tool to n8n via the MCP is different.
For per-tool instructions, check out the full MCP Setup Guide.

Here are the basic steps for Claude (the most popular app for n8n’s MCP server):

1. Enable MCP access

Navigate to Settings > Instance-level MCP. Then toggle Enable MCP access

Create n8n workflows from wherever you prompt

n8n MCP server integrates with all the most popular AI tools.

Simple sentences. Sophisticated workflows.

Here are just a few ideas of what you can build with the official n8n MCP.

David, Sales

David built a workflow that gets new leads, scores them, and then updates the CRM.

Claudia, HR

Claudia built a workflow that creates accounts for new hires and sends them a welcome message.

Luis, Marketing

Luis built an agent that checks newsletter compliance with review before posting.

Nikki, Small Business Owner

Nikki created an agent that flags urgent emails, and then drafts replies for the rest.

Workflows built + tested while you wait

You can do more with the MCP server than create and update workflows. It also comes with tools for validating workflows, running tests, and generating test data.

Here’s what a common flow looks like:

Still building by hand? Let AI workflow its magic instead

See how to get started with creating and editing n8n workflows with your favorite AI tools.

Create n8n Workflows With Agents | Official MCP

This video shows how to integrate n8n with coding agents using the official MCP. The guide covers setting up connectors within Claude Desktop and OpenCode, configuring system prompts for workflow automation, and managing credentials to set up direct interaction between LLMs and n8n instances.

Liam McGarriggle | n8n

Play video

I Don't Build Workflows Anymore | n8n MCP Live Build

In this video, I show the process of "vibe coding" a Slack-based workflow reviewer via Claude Desktop’s integration with n8n’s MCP. See how to go from technical planning to a production-ready system while managing agent interactions and error handling throughout the development cycle.

Liam McGarriggle | n8n

Play video

The Creator of n8n's MCP Shows You How to Actually Use It (3 Live Builds)

The creator of n8n’s MCP, Milorad, shows you what you can do with the MCP by building three distinct workflows. These examples show how to go from simple deterministic tasks to creating complex AI-orchestrated systems.

Dylan J Watkins | n8n

Play video

NEW n8n Skill for Claude Code!

In this video, Leonardo installs the n8n Skills plugin inside Claude Code, wires up the instance-level n8n MCP with its OAuth URL and access token, and then describes a simple workflow in plain English while Claude builds it for him.

Leonardo Grigorio

Play video

MCP guides to get you going

Agentic RAG: A Guide to Building Autonomous AI Systems

Agentic RAG: A Guide to Building Autonomous AI Systems

Agentic RAG explained: LLM-powered agents autonomously choose tools like SQL and GraphRAG to retrieve and verify answers. Build your own system with n8n.
Build a custom knowledge RAG chatbot using n8n

Build a custom knowledge RAG chatbot using n8n

Learn how to build powerful RAG chatbots with n8n's visual workflow automation. This step-by-step guide demonstrates how to connect to any knowledge source, index it in a vector database, and create an AI-powered chatbot that provides accurate, context-aware answers.
Evaluating RAG, aka Optimizing the Optimization

Evaluating RAG, aka Optimizing the Optimization

RAG isn’t foolproof. Explore common hallucinations, evaluation metrics, and how to improve RAG accuracy in n8n.
LlamaIndex vs LangChain: Which RAG tool is right for you?

LlamaIndex vs LangChain: Which RAG tool is right for you?

LangChain vs LlamaIndex: compare both RAG frameworks on ease of use, data handling, and flexibility; see when n8n is the better low-code alternative.
Practical Evaluation Methods for Enterprise-Ready LLMs

Practical Evaluation Methods for Enterprise-Ready LLMs

Discover practical evaluation methods for enterprise-ready LLMs. Learn how to measure accuracy, safety, and reliability—and see how n8n’s built-in evaluation tools make it easy to test and improve AI workflows.
Iterations, hallucinations, and lessons learned: Rebuilding our AI Assistant on n8n

Iterations, hallucinations, and lessons learned: Rebuilding our AI Assistant on n8n

We like drinking our own champagne at n8n, so when it came to rebuilding our internal AI assistant, we decided to see if we could do it using our own tooling. And as engineers who think in code, it was an enticing challenge to step away from the command line and experiment on building with workflows. It took us a few months, but we did it, and pretty successfully too! Plus, we learned some valuable lessons along the way. If you’re planning on building AI tools, we hope our endeavors will prove j

Your next workflow is only one prompt away

FAQs

Questions?