This workflow corresponds to n8n.io template #6420 — we link there as the canonical source.
This workflow follows the Agent → Chainllm 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 →
{
"id": "99QisNGBpRO6PDM1",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "GoMarble MCP - Weekly Report",
"tags": [],
"nodes": [
{
"id": "5b23d5ab-2930-4cd2-8949-9d36c95c640f",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-180,
-120
],
"parameters": {
"text": "={{ $json['report prompt'] }}",
"options": {
"systemMessage": "You are a senior digital marketing professional preparing an email to be sent to the client. There should be no made up data or hallucination. "
},
"promptType": "define"
},
"typeVersion": 1.9
},
{
"id": "cd7d0eb0-fedf-45f2-9c7f-bcd40ca15136",
"name": "Anthropic Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
"notes": "\ud83d\udd11 Add your Anthropic API credentials in the node settings",
"position": [
-220,
100
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "claude-sonnet-4-20250514",
"cachedResultName": "Claude Sonnet 4"
},
"options": {}
},
"typeVersion": 1.3
},
{
"id": "87a91c08-5c64-4dfa-9542-53ac14bd5337",
"name": "MCP Client",
"type": "@n8n/n8n-nodes-langchain.mcpClientTool",
"notes": "\ud83d\udd10 Add your GoMarble Bearer YOUR_TOKEN_HERE - get it from https://www.gomarble.ai/docs/connect-to-n8n",
"position": [
20,
100
],
"parameters": {
"sseEndpoint": "https://apps.gomarble.ai/mcp-api/sse",
"authentication": "bearerAuth"
},
"typeVersion": 1
},
{
"id": "8953ebc8-7632-48a3-ae8d-d8d201e9db47",
"name": "Gmail",
"type": "n8n-nodes-base.gmail",
"notes": "\ud83d\udce7 Configure your Gmail credentials and set the recipient email address",
"position": [
520,
-120
],
"parameters": {
"sendTo": "",
"message": "={{ $json.text }}",
"options": {},
"subject": "Weekly platform analysis report"
},
"typeVersion": 2.1
},
{
"id": "e8670179-2f5e-45b1-873f-896eec4150b0",
"name": "Schedule Trigger",
"type": "n8n-nodes-base.scheduleTrigger",
"notes": "\u23f0 Runs every Monday at 8 AM - adjust schedule as needed",
"position": [
-560,
-120
],
"parameters": {
"rule": {
"interval": [
{
"field": "weeks",
"triggerAtDay": [
1
],
"triggerAtHour": 8
}
]
}
},
"typeVersion": 1.2
},
{
"id": "9ef2ba81-e746-47aa-84e6-962fa9cfa5fa",
"name": "Basic LLM Chain1",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
180,
-120
],
"parameters": {
"text": "=You are an expert in converting marketing reports into clean, well-styled HTML for email. Convert the following input into final HTML using the GoMarble brand theme and colors.\n\nDesign Guidelines:\n- Background: #00272B\n- Card Backgrounds: #033438\n- Subtle Sections / Dividers: #013135\n- Primary Text: #EAFDFC\n- Secondary Text: #B8FFF6\n- Tertiary Text: #8AD9D1\n- Borders: #00A0AF\n- Accent (CTA or highlight): #FFC66C\n- Error or alerts: #FF6B6B\n- Font: -apple-system, BlinkMacSystemFont, 'Segoe UI', Helvetica, Arial, sans-serif\n- Headings: #EAFDFC, font-weight: 600\u2013700\n- Body Text: #B8FFF6\n- Use clean, modern padding, card-style sections, and well-aligned tables\n- KPI and campaign tables must have alternating row colors (#013135 / #033438), bold header row, bordered cells using #00A0AF\n- Section headings should have ample top margin, bold weight, and primary text color\n- Use <div>-based layout with section wrappers (cards), avoid raw <br> for spacing\n- Final HTML must be suitable for pasting directly into an email node \u2014 no CSS in <head>, use inline styles only\n- Output should be ONLY the inner HTML (no <html>, <head>, <body>, or comments)\n- Do not include any explanation or extra output \u2014 just the final HTML\n\nInput report:\n{{ $json.output }}",
"promptType": "define"
},
"typeVersion": 1.6
},
{
"id": "ffa751d7-2632-4165-91d4-991f6846b7f9",
"name": "OpenAI Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"notes": "\ud83e\udd16 Configure your OpenAI API credentials for HTML formatting",
"position": [
300,
120
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "chatgpt-4o-latest",
"cachedResultName": "chatgpt-4o-latest"
},
"options": {}
},
"typeVersion": 1.2
},
{
"id": "fcc765ef-7e8a-4d41-8b69-1f3e40094cfb",
"name": "Report Prompt",
"type": "n8n-nodes-base.set",
"notes": "\ud83d\udcdd Customize the report prompt for your specific account and requirements",
"position": [
-360,
-120
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "f100cea7-e5ea-4dce-b69b-6739ccdfa543",
"name": "report prompt",
"type": "string",
"value": "=You are senior performance-marketing analyst. \nVoice: sharp, concise, insight-driven (no fluff, no marketing hype). \nGoal: craft a weekly digest that a busy CMO can scan in <3 min and act on immediately.\nAd Account: [YOUR_ACCOUNT_NAME]; Time Period: Last 7 days\nUse Meta & Google Ads account data to create the report.\n\n1. Executive Snapshot (3-line paragraph)**\n \u2022 One-sentence topline: combined spend, revenue, ROAS and WoW % change. \n \u2022 One-sentence highlight of the biggest win. \n \u2022 One-sentence note on the main risk / action gap. \n\n**2. KPI Tables** \n A. *Channel Overview* \u2014 columns: Platform, Spend, Impr, Clicks, CTR, CPC, Conv, CPA, Revenue, ROAS, WoW \u0394-ROAS%. \n B. *Top 3 Campaigns (per platform)* \u2014 ranked by ROAS. Include objective and primary creative hook. \n C. Any *Underperformers* \n\n**3. Give 2-3 Action Recommendations"
}
]
}
},
"typeVersion": 3.4
}
],
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "45311444-f920-4b15-9d30-b6a76a8af36f",
"connections": {
"Gmail": {
"main": [
[]
]
},
"AI Agent": {
"main": [
[
{
"node": "Basic LLM Chain1",
"type": "main",
"index": 0
}
]
]
},
"MCP Client": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Report Prompt": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
},
"Basic LLM Chain1": {
"main": [
[
{
"node": "Gmail",
"type": "main",
"index": 0
}
]
]
},
"Schedule Trigger": {
"main": [
[
{
"node": "Report Prompt",
"type": "main",
"index": 0
}
]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "Basic LLM Chain1",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Anthropic Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
}
}
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
Transform your marketing data into actionable insights with this intelligent automation workflow. The system combines scheduled triggers with AI-powered analysis to deliver comprehensive marketing reports directly to your inbox.
Source: https://n8n.io/workflows/6420/ — 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.
The Multi-Model Agency Content Engine is a high-performance editorial system designed for agencies. It solves the "blank page" problem by alternating between real-world social proof and strategic expe
This workflow automates the creation, rendering, approval, and posting of TikTok-style POV (Point of View) videos to Instagram, with cross-posting to Facebook and YouTube. It eliminates manual video p
This n8n-powered workflow automates the entire lifecycle of real estate lead intake, qualification, routing, assignment, and reporting across multiple channels. It brings WhatsApp inquiries and websit
kisisel asistan. Uses toolWorkflow, toolHttpRequest, toolCalculator, toolThink. Scheduled trigger; 43 nodes.
My workflow 14. Uses rssFeedRead, chainLlm, lmChatOpenAi, openWeatherMap. Scheduled trigger; 40 nodes.