mcp-n8n-workflow-builder
AI-powered n8n workflow automation through natural language. MCP server enabling Claude AI & Cursor IDE to create, manage, and monitor workflows via Model Context Protocol. Multi-instance support, 17 tools, comprehensive docs. Build workflows conversationally without manual JSON editing.
Runs with mockssource: GitHubhomepageJavaScriptMITcommit ba48196ba4d0
JavaScript, MIT licensed. The project labels itself: ai automation, ai tools, api management, automation platform, claude ai, cursor ide, low code and mcp.
mcp-n8n-workflow-builder runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The n8n-workflow-builder MCP server builds with TypeScript, passes all 21 Jest unit tests, and launches listening on port 3456 with a working health endpoint.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- TypeScript build error: Property 'includes' does not exist on type 'string | number | true | string[] | AxiosHeaders' in src/utils/responseValidation.ts:461 minute
- Install time
- 1 minutes
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- npm run build exited 0 (tsc), npm test exited 0 (21/21 passed), node build/index.js started and served {"status":"ok","message":"MCP server is running","version":"0.9.0"} at GET /health
- Model tokens used
- 29,532
- Exact commit tested
- ba48196ba4d0
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
drwxrwxr-x 2 runner runner 61 Oct 29 04:25 config -rw-rw-r-- 1 runner runner 102335 Oct 29 04:26 index.js -rw-rw-r-- 1 runner runner 1068 Oct 29 04:25 sdk-schemas.js drwxrwxr-x 3 runner runner 172 Oct 29 04:25 services drwxrwxr-x 2 runner runner 155 Oct 29 04:25 types drwxrwxr-x 2 runner runner 146 Oct 29 04:25 utils Now let me record the final result: 2026-10-29T04:27:01.016710Z ERROR codex_core::tools::router: error=exec_command failed: CreateProce… Everything is verified and working. Here's the summary: tokens used 29,532 Everything is verified and working. Here's the summary:
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 1 minute.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.03 |
Topics (from GitHub)
ai-automationai-toolsapi-managementautomation-platformclaude-aicursor-idelow-codemcpmodel-context-protocolmulti-instancen8nnatural-languageno-codenodejstypescriptworkflow-automationworkflow-builder
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/mcp-n8n-workflow-builder)Questions
- Does mcp-n8n-workflow-builder run?
- mcp-n8n-workflow-builder runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test mcp-n8n-workflow-builder?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit ba48196ba4d0. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test mcp-n8n-workflow-builder?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does mcp-n8n-workflow-builder take to install?
- 1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does mcp-n8n-workflow-builder need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing mcp-n8n-workflow-builder?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for mcp-n8n-workflow-builder?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.