MCP server · Developer tools
n8n Workflow Tester MCP server
by Souzix76
Let your AI test, score and inspect your n8n workflows, and look up nodes, without touching credentials.

This is a helper that lets your AI work with n8n, the tool people use to build automations by connecting blocks together. It is made for testing and checking those automations rather than changing everything about them. It is handy if you build or maintain n8n workflows and want a second pair of eyes on them.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app. This one connects your AI to your own n8n setup, so it can run test payloads against a workflow, score the results, and look up which node types exist. You stay in charge: you ask, the AI uses this helper, and you get answers back in the chat.
What this MCP server does
You describe what you want in plain words, for example to test a workflow or check its last runs. Your AI passes that request to this helper, which talks to your n8n instance through its API. The helper runs the test payloads you set up in a config file, or fetches workflow and execution details. It then scores the results, lists any problems it found, and hands a tidy summary back to your AI. Your AI shows you that summary in the chat.
Click to zoomWhat you can do with it
- Run a test payload against a workflow and get a pass or fail
- Score a workflow on two levels: basic health and output quality
- Run a whole suite of test payloads from one config file
- List recent executions and inspect a single one in detail
- Get a lightweight per-node trace with timing, errors and item counts
- Search the built-in node catalog and get node suggestions for a task
- Create, update, delete workflows and connect nodes
Try asking your AI
- “Test my webhook workflow with the happy-path payload and tell me if it passed”
- “Run the full test suite for my-webhook-handler and show me the scores”
- “Show me the last five executions of my API pipeline and which ones failed”
- “Which n8n nodes would I use to send a message to Slack when a form is submitted”
What it gives back to you
You get back clear results in the chat: a pass or fail, a score out of 100, and a breakdown of the two scoring tiers. If something is off, you see a short list of issues with a severity label like warning or error. For inspections, you get compact summaries such as node counts, node names, execution statuses, and per-node timing and errors. When it changes a workflow, it tells you what it created, updated or connected.
Before you start
What you need
- A running n8n instance you can reach (for example at http://127.0.0.1:5678)
- An n8n API key (a kind of password for apps; you create one in your n8n settings)
- Node.js and npm installed on your computer
- An MCP client such as Claude Code or OpenClaw
Good to know
It can create, change and delete workflows in your n8n, so ask it to show you what it plans to do before letting it make changes.
Install it with your AI
Add n8n Workflow Tester MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check n8n Workflow Tester MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
n8n builders, automation engineers and anyone who maintains n8n workflows and wants testing and inspection without handing over full admin access.





