Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.getmuster.io/llms.txt

Use this file to discover all available pages before exploring further.

​
How it works

The n8n connector:
  • Discovers all n8n workflows containing LLM nodes automatically
  • Streams execution results by polling the n8n Execution API every 30 seconds
  • Infers quality checks from execution output
Elitery deploys and manages the connector. Your n8n workflow developers do nothing.

​
What Elitery needs from you

During onboarding, provide: 
N8N_BASE_URL=https://n8n.yourcompany.internal
N8N_API_KEY=<from n8n Settings → API>
If your n8n uses a self-signed TLS certificate: 
N8N_SKIP_TLS_VERIFY=true

​
Which workflows are monitored

The connector automatically identifies AI workflows by detecting LLM nodes:
  • @n8n/n8n-nodes-langchain.agent
  • @n8n/n8n-nodes-langchain.openAi
  • @n8n/n8n-nodes-langchain.lmChatOpenAi
  • @n8n/n8n-nodes-langchain.lmChatAnthropic
  • n8n-nodes-base.openAi
Non-AI workflows (data pipelines, email triggers, etc.) are ignored.

​
What your n8n developers do

Nothing for automatic monitoring. For precise quality checks on critical workflows, add an HTTP Request node as the last step: Node settings:
SettingValue
MethodPOST
URLhttps://api.yourcompany.getmuster.io/api/v1/jobs/{{ $json.jobId }}/quality
BodyJSON (see below)
{
  "agent_id": "invoice-processing-n8n",
  "checks": [
    {
      "check_id": "output_not_empty",
      "severity": "HIGH",
      "passed": "{{ $json.output !== null && $json.output !== '' }}"
    },
    {
      "check_id": "required_field_present",
      "severity": "HIGH",
      "passed": "{{ $json.total !== undefined }}"
    }
  ]
}
This is optional — the connector already provides automatic monitoring without it.