Website tool get an error then quits

Describe the problem/error/question

I’ve got an AI agent with a website tool that’s doing a get for my lab box. When the docker container for the website is up everything’s fine, but when I do a docker stop on the website and try to execute the AI Agent I immediately get an error and stops, it doesn’t return back to the AI Agent so that it can figure out that the site is down.

What is the error message (if any)?

Problem in node ‘Website tool‘

The service refused the connection - perhaps it is offline

Please share your workflow

{“nodes”: [{“parameters”: {},“type”: “n8n-nodes-base.manualTrigger”,“typeVersion”: 1,“position”: [0,0],“id”: “7fe76fea-7298-4326-909f-cc36879aec16”,“name”: “When clicking ‘Execute workflow’”},{“parameters”: {“options”: {“systemMessage”: “You are Mia, an IT Administrator for Unix4u. As a new employee, your only responsibility is to ensure the website at http://10.0.0.15:8090/ is operational. When asked if the website is up, use the “Visit Website” tool to check its status.\n\n1. Access the website using the provided HTTP tool.\n\n2. The website is considered up and operational only if the response contains the HTML content: Unix4u rocks . Any tcp errors should consider the site down.\n\n3. Report the website’s status as either “up :smiling_face_with_sunglasses::+1:” or “down :disappointed_face::-1:” based on the tool’s response.”}},“type”: “/n8n-nodes-langchain.agent”,“typeVersion”: 3,“position”: [224,96],“id”: “37625ecd-a347-49bc-bf36-ff1c7019b27f”,“name”: “AI Agent”,“retryOnFail”: false,“executeOnce”: false,“onError”: “continueErrorOutput”},{“parameters”: {“model”: {“__rl”: true,“value”: “gpt-5-nano”,“mode”: “list”,“cachedResultName”: “gpt-5-nano”},“options”: {}},“type”: “/n8n-nodes-langchain.lmChatOpenAi”,“typeVersion”: 1.2,“position”: [64,384],“id”: “18b2a47c-4ecc-475f-b65c-0ebf84c76e1a”,“name”: “OpenAI Chat Model”,“credentials”: {“openAiApi”: {“id”: “KEA4EzgvHjpxgqKl”,“name”: “OpenAi account”}}},{“parameters”: {},“type”: “/n8n-nodes-langchain.memoryBufferWindow”,“typeVersion”: 1.3,“position”: [224,384],“id”: “ad06938a-b371-4eeb-8233-457af8342b54”,“name”: “Simple Memory”},{“parameters”: {“options”: {}},“type”: “/n8n-nodes-langchain.chatTrigger”,“typeVersion”: 1.3,“position”: [0,192],“id”: “f2d79dd7-f6f6-4200-9c16-cbb27fd8e55a”,“name”: “is the website up?”,“webhookId”: “c4711fff-1b83-4090-b4b1-83c45c92a283”},{“parameters”: {“url”: “http://lab.unix4u.us:8090”,“options”: {}},“type”: “n8n-nodes-base.httpRequestTool”,“typeVersion”: 4.3,“position”: [448,384],“id”: “b5bd985f-f1d8-4abf-8a12-e29feb8e7348”,“name”: “Website tool”,“notesInFlow”: false}],“connections”: {“When clicking ‘Execute workflow’”: {“main”: [[{“node”: “AI Agent”,“type”: “main”,“index”: 0}]]},“OpenAI Chat Model”: {“ai_languageModel”: [[{“node”: “AI Agent”,“type”: “ai_languageModel”,“index”: 0}]]},“Simple Memory”: {“ai_memory”: [[{“node”: “AI Agent”,“type”: “ai_memory”,“index”: 0}]]},“is the website up?”: {“main”: [[{“node”: “AI Agent”,“type”: “main”,“index”: 0}]]},“Website tool”: {“ai_tool”: [[{“node”: “AI Agent”,“type”: “ai_tool”,“index”: 0}]]}},“pinData”: {},“meta”: {“templateCredsSetupCompleted”: true,“instanceId”: “9992bc833cb1ab38ebd95d00167b9439a6972c99420ad276b3bf893cdd569fd7”}}

Problem in node ‘Website tool‘

Problem in node ‘Website tool‘

Share the output returned by the last node

No parameters are set up to be filled by AI. Click on the :sparkles: button next to a parameter to allow AI to set its value.

The service refused the connection - perhaps it is offlineError detailsFrom HTTP RequestError codeECONNREFUSEDFull messageconnect ECONNREFUSED 10.0.0.15:8090Request{ “headers”: { “accept”: “application/json,text/html,application/xhtml+xml,application/xml,text/;q=0.9, image/;q=0.8, /;q=0.7” }, “method”: “GET”, “uri”: “http://lab.unix4u.us:8090”, “gzip”: true, “rejectUnauthorized”: true, “followRedirect”: true, “resolveWithFullResponse”: true, “followAllRedirects”: true, “timeout”: 300000, “encoding”: null, “json”: false, “useStream”: true }Other infoItem Index0Node typen8n-nodes-base.httpRequestToolNode version4.3 (Latest)n8n version1.117.3 (Self Hosted)Time10/30/2025, 3:19:44 PMStack traceNodeApiError: The service refused the connection - perhaps it is offline at ExecuteContext.execute (/usr/lib/node_modules/n8n/node_modules/n8n-nodes-base/nodes/HttpRequest/V3/HttpRequestV3.node.ts:850:16) at processTicksAndRejections (node:internal/process/task_queues:105:5) at WorkflowExecute.executeNode (/usr/lib/node_modules/n8n/node_modules/n8n-core/src/execution-engine/workflow-execute.ts:1093:8) at WorkflowExecute.runNode (/usr/lib/node_modules/n8n/node_modules/n8n-core/src/execution-engine/workflow-execute.ts:1274:11) at /usr/lib/node_modules/n8n/node_modules/n8n-core/src/execution-engine/workflow-execute.ts:1708:27 at /usr/lib/node_modules/n8n/node_modules/n8n-core/src/execution-engine/workflow-execute.ts:2324:11

Information on your n8n setup

n8n version:1.117.3

Database (default: SQLite): postgressql

n8n EXECUTIONS_PROCESS setting (default: own, main): dunno what this mean

Running n8n via (Docker, npm, n8n cloud, desktop app): npm

Operating system: ubuntu 24.04 x64

I’m trying to follow networkchuck’s video @ https://www.youtube.com/watch?v=budTmdQfXYU so (except for the VPS) it’s setup the same way as he did.

Hello @DrMastermind

Yes, I think there’s something wrong with the AI Agent node version 3 behavior when the tool encounters an error,

Please try version 2.2 and let me know if it works:

Please copy this workflow, paste it, and give it a try..

3 Likes

thank you. That fixed it!

1 Like

Thanks for confirming..
I’ve noticed several issues about AI Agent issues in v3, I hope the team is aware of these problems or can clarify how the new changes are intended to work..

I wish I had seen this before I created a work around. Thanks for sharing!

1 Like

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.