This workflow corresponds to n8n.io template #4272 — we link there as the canonical source.
This workflow follows the Agent → Chat Trigger recipe pattern — see all workflows that pair these two integrations.
The workflow JSON
Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →
{
"name": "My workflow",
"tags": [],
"nodes": [
{
"id": "b52ee9e9-f809-4c42-bb5c-b27df72b4695",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-60,
160
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "344b64aa-683b-43dd-9f10-2d3c67dae753",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
460,
20
],
"parameters": {
"options": {
"systemMessage": "You are an expert web scraping assistant with access to Bright Data's Web Unlocker API. This gives you the ability to execute a specific set of actions. When using tools, you must share across the exact name of the tool for it to be executed.\n\nFor example, \"Search Engine Scraping\" should be \"search_engine\""
}
},
"retryOnFail": true,
"typeVersion": 1.9
},
{
"id": "9c998783-2477-4131-a1e6-a7a8fa09229f",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
220,
220
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1",
"cachedResultName": "gpt-4.1"
},
"options": {}
},
"typeVersion": 1.2
},
{
"id": "bc8e349a-ab20-446c-9fbe-e6d46c9db60e",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
360,
200
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "e3d838ca-9a85-46cc-b2bd-664d12711ff1",
"name": "List MCP Tools",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
480,
220
],
"parameters": {},
"credentials": {},
"typeVersion": 1
},
{
"id": "eec892f3-a008-4328-b0e0-914bf80068b5",
"name": "Scrape SERP Results",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
620,
200
],
"parameters": {},
"credentials": {},
"typeVersion": 1
},
{
"id": "9cf2ccee-fe17-4997-87f0-7686a3194e14",
"name": "Scrape Webpage",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
760,
220
],
"parameters": {},
"credentials": {},
"typeVersion": 1
},
{
"id": "a681c0f5-3dfe-43c1-88a8-4b9ccf348e50",
"name": "Send the custom newsletter via email",
"type": "n8n-nodes-base.emailSend",
"position": [
820,
20
],
"parameters": {
"html": "={{ $json.output }}",
"options": {},
"subject": "Today's Headlines",
"toEmail": "<user@example.com>",
"fromEmail": "<user@example.com>"
},
"typeVersion": 2.1
},
{
"id": "2615c5b3-41fd-474b-8e7e-7b1d1ae31f35",
"name": "AI news collection prompt",
"type": "n8n-nodes-base.set",
"position": [
160,
-40
],
"parameters": {
"mode": "raw",
"options": {},
"jsonOutput": "{\n \"sessionId\": \"google\",\n \"chatInput\": \"get the latest news from https://www.brightdata.com/blog and https://www.theguardian.com/us with your scrape_as_markdown and Google News with your search engine tool to find the latest global headlines--pull actual headlines, not just the site description.\"\n}\n"
},
"typeVersion": 3.4
},
{
"id": "3ad29ec6-0b3a-437d-a386-4867bdc1197e",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
140,
-160
],
"parameters": {
"width": 150,
"height": 100,
"content": "Injecting the AI news collection prompt for GPT-4.1"
},
"typeVersion": 1
},
{
"id": "6475bd91-134b-47c6-805d-758f1569e132",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
180,
340
],
"parameters": {
"width": 150,
"height": 80,
"content": "Connect using your OpenAI credentials"
},
"typeVersion": 1
},
{
"id": "8cb0c078-c891-45f8-98d3-5114d08bf887",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
800,
-80
],
"parameters": {
"width": 150,
"height": 80,
"content": "Set up with recipient and SMTP information"
},
"typeVersion": 1
},
{
"id": "6f6f3497-2d26-4cd3-a442-b087f642a09f",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
500,
-100
],
"parameters": {
"width": 160,
"height": 100,
"content": "Connecting to both Bright Data's MCP and your GPT model with memory"
},
"typeVersion": 1
},
{
"id": "8954f050-7a5e-4abe-a478-65092b726efe",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"position": [
-60,
-40
],
"parameters": {
"rule": {
"interval": [
{
"triggerAtHour": 9
}
]
}
},
"typeVersion": 1.2
},
{
"id": "adf00b09-e9fe-464f-bf76-cf34f4866760",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-80,
-140
],
"parameters": {
"width": 150,
"height": 80,
"content": "Choose the interval that works best for you"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "",
"connections": {
"AI Agent": {
"main": [
[
{
"node": "Send the custom newsletter via email",
"type": "main",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "AI news collection prompt",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"AI news collection prompt": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
}
}
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Disclaimer: This template is for self-hosted n8n instances only.
Source: https://n8n.io/workflows/4272/ — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This n8n workflow template uses community nodes and is only compatible with the self-hosted version of n8n.
This workflow automates patient care coordination in healthcare settings by intelligently processing patient information and scheduling follow-up communications through multiple channels. Designed for
This template obtains all the possible tools from Bright Data MCP, process this through chatbot, then run any tool based on the user's query
💥🛠️Build a Web Search Chatbot with GPT-4o and MCP Brave Search. Uses agent, chatTrigger, n8n-nodes-mcp, memoryBufferWindow. Chat trigger; 15 nodes.
Disclaimer: This workflow only works with local installations of n8n because it uses a community MCP node