{ "id": "3I6NhpsV8GD-UKj7da3lh", "meta": { "templateCredsSetupCompleted": true }, "name": "AI-Powered SEO Cannibalization Monitor: Databox, Google Search Console & Slack", "tags": [], "nodes": [ { "id": "36b758bc-c73b-42b1-9490-104251f4dde2", "name": "Weekly SEO Monitor", "type": "n8n-nodes-base.scheduleTrigger", "position": [ -1472, 704 ], "parameters": { "rule": { "interval": [ { "field": "weeks", "triggerAtDay": [ 1 ], "triggerAtHour": 9 } ] } }, "typeVersion": 1.3 }, { "id": "d7c022ca-9d9a-4b4d-9efa-b498f3ac547a", "name": "GPT-4o Model2", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ 240, 880 ], "parameters": { "model": { "__rl": true, "mode": "id", "value": "gpt-4o" }, "options": { "temperature": 0.2 }, "builtInTools": {} }, "credentials": { "openAiApi": { "name": "" } }, "typeVersion": 1.3 }, { "id": "ae52cfe1-fe3c-4b64-ab0d-9562ecbcde1d", "name": "Loop Over Items", "type": "n8n-nodes-base.splitInBatches", "position": [ -1024, 704 ], "parameters": { "options": {} }, "typeVersion": 3 }, { "id": "932f3040-cfc6-4cef-ae22-e2d38957b232", "name": "Aggregate3", "type": "n8n-nodes-base.aggregate", "position": [ -800, 80 ], "parameters": { "options": {}, "fieldsToAggregate": { "fieldToAggregate": [ { "fieldToAggregate": "message.text" } ] } }, "typeVersion": 1 }, { "id": "a6a2e780-dc6f-4747-90b0-ab0cbcc3be69", "name": "OpenAI Chat Model1", "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi", "position": [ -576, 256 ], "parameters": { "model": { "__rl": true, "mode": "list", "value": "gpt-4.1-mini" }, "options": {}, "builtInTools": {} }, "credentials": { "openAiApi": { "name": "" } }, "typeVersion": 1.3 }, { "id": "ec32497b-42f9-4a48-9d6d-3fa1739719b9", "name": "Set client data", "type": "n8n-nodes-base.code", "position": [ -1248, 704 ], "parameters": { "jsCode": "return [\n {\n json: {\n client: \"Acme Retail\",\n google_search_console_data_source_id: 4907543,\n metrics: {\n impressions: \"GoogleSearchConsole@impressions\",\n position: \"GoogleSearchConsole@position\"\n }\n }\n },\n {\n json: {\n client: \"BlueWave Agency\",\n google_search_console_data_source_id: 4907544,\n metrics: {\n impressions: \"GoogleSearchConsole@impressions\",\n position: \"GoogleSearchConsole@position\"\n }\n }\n },\n {\n json: {\n client: \"Nexus Health\",\n google_search_console_data_source_id: 4907545,\n metrics: {\n impressions: \"GoogleSearchConsole@impressions\",\n position: \"GoogleSearchConsole@position\"\n }\n }\n }\n];" }, "typeVersion": 2 }, { "id": "4948acee-125d-445e-8519-6805b6624004", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [ -2336, -48 ], "parameters": { "width": 672, "height": 1472, "content": "# AI-Powered SEO Cannibalization Monitor: Databox, Google Search Console & Slack\n\nThis workflow runs weekly and checks multiple client websites for potential SEO cannibalization issues using Google Search Console data from Databox.\n\nIt pulls page-level **impressions** and **average position** data, prepares the data, analyzes it with AI, and sends SEO risk reports to Slack.\n\n## Who\u2019s it for\n\n* SEO agencies managing multiple clients\n* Client success or account managers who need weekly SEO visibility\n* SEO leads who want a high-level view of client risks\n\n## How it works\n\n* A weekly trigger starts the workflow.\n* The first Code node contains the client list and Databox metric setup.\n* The loop processes each client one by one.\n* Databox pulls Google Search Console impressions and average position data.\n* The data is merged, cleaned, and filtered to remove low-traffic pages.\n* The first AI agent checks each client for possible SEO cannibalization.\n* A Slack alert is sent with the client-level findings.\n* After all clients are processed, a second AI agent creates a combined leadership summary.\n* The final cross-client report is sent to Slack.\n\n## How to set up\n\n1. Connect the **Databox MCP Client Tool** with your endpoint and authentication headers.\n2. Add your clients in the first **Code** node, including:\n * Client name\n * Google Search Console data source ID\n * Impressions metric key\n * Average position metric key\n3. Connect your **OpenAI** credentials.\n4. Connect the **Slack** nodes to the right channels.\n5. Adjust the weekly schedule if needed.\n\nYou can ask **Databox Genie** to provide the correct data source IDs and metric keys for each client, then format them in the same structure as the example Code node.\n\n## Requirements\n\n* n8n 1.0+\n* Databox MCP access\n* Google Search Console data available in Databox\n* OpenAI credentials\n* Slack workspace\n\n## Output\n\nThe workflow sends two reports:\n\n* **Client-level report:** highlights possible cannibalization issues for each client.\n* **Leadership report:** summarizes SEO risks across all processed clients." }, "typeVersion": 1 }, { "id": "619a971a-de80-40fd-b1ff-b2492178a9f8", "name": "GSC impressions", "type": "@n8n/n8n-nodes-langchain.mcpClient", "position": [ -736, 624 ], "parameters": { "tool": { "__rl": true, "mode": "list", "value": "load_metric_data", "cachedResultName": "load_metric_data" }, "options": {}, "parameters": { "value": { "end_date": "={{ $now.toFormat('yyyy-MM-dd') }}", "dimension": "page", "metric_key": "={{ $json.metrics.impressions }}", "start_date": "={{ $now.minus({ days: 7 }).toFormat('yyyy-MM-dd') }}", "data_source_id": "={{ $json.google_search_console_data_source_id }}" }, "schema": [ { "id": "data_source_id", "type": "number", "display": true, "removed": false, "required": true, "displayName": "data_source_id", "defaultMatch": false }, { "id": "metric_key", "type": "string", "display": true, "removed": false, "required": true, "displayName": "metric_key", "defaultMatch": false }, { "id": "start_date", "type": "string", "display": true, "removed": false, "required": true, "displayName": "start_date", "defaultMatch": false }, { "id": "end_date", "type": "string", "display": true, "removed": false, "required": true, "displayName": "end_date", "defaultMatch": false }, { "id": "dimension", "type": "string", "display": true, "removed": false, "required": false, "displayName": "dimension", "defaultMatch": false }, { "id": "granulation_time_unit", "type": "string", "display": true, "removed": true, "required": false, "displayName": "granulation_time_unit", "defaultMatch": false }, { "id": "is_whole_range", "type": "boolean", "display": true, "removed": true, "required": false, "displayName": "is_whole_range", "defaultMatch": false }, { "id": "record_limit", "type": "string", "display": true, "removed": true, "required": false, "displayName": "record_limit", "defaultMatch": false } ], "mappingMode": "defineBelow", "matchingColumns": [], "attemptToConvertTypes": false, "convertFieldsToString": false }, "endpointUrl": "https://mcp.databox.com/mcp", "authentication": "mcpOAuth2Api" }, "credentials": { "mcpOAuth2Api": { "name": "" } }, "typeVersion": 1 }, { "id": "a4826ece-cdca-4ffa-8329-384c51ab82c2", "name": "GSC position", "type": "@n8n/n8n-nodes-langchain.mcpClient", "position": [ -736, 768 ], "parameters": { "tool": { "__rl": true, "mode": "list", "value": "load_metric_data", "cachedResultName": "load_metric_data" }, "options": {}, "parameters": { "value": { "end_date": "={{ $now.toFormat('yyyy-MM-dd') }}", "dimension": "page", "metric_key": "={{ $json.metrics.position }}", "start_date": "={{ $now.minus({ days: 7 }).toFormat('yyyy-MM-dd') }}", "data_source_id": "={{ $json.google_search_console_data_source_id }}" }, "schema": [ { "id": "data_source_id", "type": "number", "display": true, "removed": false, "required": true, "displayName": "data_source_id", "defaultMatch": false }, { "id": "metric_key", "type": "string", "display": true, "removed": false, "required": true, "displayName": "metric_key", "defaultMatch": false }, { "id": "start_date", "type": "string", "display": true, "removed": false, "required": true, "displayName": "start_date", "defaultMatch": false }, { "id": "end_date", "type": "string", "display": true, "removed": false, "required": true, "displayName": "end_date", "defaultMatch": false }, { "id": "dimension", "type": "string", "display": true, "removed": false, "required": false, "displayName": "dimension", "defaultMatch": false }, { "id": "granulation_time_unit", "type": "string", "display": true, "removed": true, "required": false, "displayName": "granulation_time_unit", "defaultMatch": false }, { "id": "is_whole_range", "type": "boolean", "display": true, "removed": true, "required": false, "displayName": "is_whole_range", "defaultMatch": false }, { "id": "record_limit", "type": "string", "display": true, "removed": true, "required": false, "displayName": "record_limit", "defaultMatch": false } ], "mappingMode": "defineBelow", "matchingColumns": [], "attemptToConvertTypes": false, "convertFieldsToString": false }, "endpointUrl": "https://mcp.databox.com/mcp", "authentication": "mcpOAuth2Api" }, "credentials": { "mcpOAuth2Api": { "name": "" } }, "typeVersion": 1 }, { "id": "27ee8c1a-97ca-44b5-8b2a-b5ea40d09054", "name": "SEO Keyword Cannibalization Detector", "type": "@n8n/n8n-nodes-langchain.agent", "position": [ 240, 704 ], "parameters": { "text": "={{ $json }}", "options": { "systemMessage": "=**ROLE**: Senior SEO Forensic Strategist & Multi-Client Auditor.\n**OBJECTIVE**: Identify and resolve \"Keyword Cannibalization\" across diverse client portfolios. You analyze 7-day performance data to detect internal competition that suppresses organic growth.\n\n**CORE PROTOCOL**:\n1. **Dynamic Context**: For every execution, identify the client name from the `client_name` field.\n2. **Universal Analysis**: Treat the URLs in the `seo_summary` as the absolute search footprint.\n3. **Intent Logic**: You must distinguish between \"Commercial Intent\" (Pricing/Services) and \"Informational Intent\" (Blogs/Guides).\n\n**DIAGNOSTIC CRITERIA**:\n- *Critical Conflict*: Two or more URLs from the same client ranking in positions 4\u201315 for the same topic.\n- *Authority Erosion*: A newer blog post is out-performing an evergreen service page, confusing Google's primary ranking choice.\n\n**RESOLUTION TYPES**:\n- *301 Redirect*: Kill the \"weak\" URL and pass juice to the \"strong\" URL.\n- *Canonicalization*: Keep both for users, but nominate one for Google.\n- *Pillar Merge*: Combine thin, competing pages into one high-authority \"Super-Page.\"\n\n---\n\n### **EXPANDED REPORT TEMPLATE (Slack-Ready)**\n\n*----- \ud83d\udee1\ufe0f SEO FORENSIC AUDIT: [Client Name] -----*\n\n\ud83d\udea8 *CANNIBALIZATION CRITICAL ALERT*\n*Primary Conflict Cluster*: [Cluster Name based on URL slugs]\n- *URL 1*: [URL] (Pos: [X] | Impr: [Y])\n- *URL 2*: [URL] (Pos: [X] | Impr: [Y])\n\n\ud83e\uddd0 *STRATEGIC DIAGNOSIS*\n[Deep 2-3 sentence analysis of the conflict. Explain how \"split authority\" is preventing a Top 3 ranking and keeping these URLs trapped in the \"Ranking Graveyard\" of Page 2.]\n\n\ud83d\udcc8 *OPPORTUNITY COST*\n- *Current State*: Organic traffic is fragmented across [X] similar paths.\n- *Potential Gain*: By consolidating authority, the projected rank for this cluster is *Top 3*, which typically yields a 3x increase in Click-Through Rate (CTR).\n\n\ud83d\udee0\ufe0f *RECOVERY ROADMAP*\n- *Recommended Action*: [Redirect / Canonical / Merge]\n- *Authority Winner*: [The URL that should remain the primary]\n- *Next Tactical Step*: [One specific instruction for the technical team to execute immediately.]" }, "promptType": "define", "hasOutputParser": true }, "typeVersion": 3.1 }, { "id": "2df0d58a-1ca2-45e0-9dc7-6c8d5e702f7e", "name": "SEO Keyword Cannibalization Detector 2", "type": "@n8n/n8n-nodes-langchain.agent", "position": [ -576, 80 ], "parameters": { "text": "={{ $json }}", "options": { "systemMessage": "=**Role**: Director of SEO Operations.\n**Objective**: Synthesize multiple complex SEO forensic audits into a single \"High-Signal\" executive briefing.\n\n**Core Protocol**:\n- You will receive an array of individual client cannibalization reports.\n- Your task is to process the entire portfolio and output exactly **one sentence** per client.\n- Focus on the **Severity of the Conflict** and the **Ranking Potential**.\n- Use single asterisks (*) for bolding to ensure Slack compatibility.\n\n**Briefing Logic**:\n- *[CRITICAL]*: If multiple Page 2 URLs exist -> Focus on the \"Top 3 Opportunity\" via consolidation.\n- *[OVERLAP]*: If blog posts are killing service pages -> Focus on \"Intent Protection.\"\n- *[STABLE]*: If conflict is low -> Focus on \"Authority Maintenance.\"\n\n**Output Structure (Slack-Ready)**:\n\n\ud83d\ude80 *PORTFOLIO SEO INTELLIGENCE BRIEF* \ud83d\ude80\n*Portfolio Status*: [Daily/Weekly] Operational Audit\n\n---\n*EXECUTIVE CLIENT SUMMARIES:*\n- *[Client Name A]*: [One-sentence insight: Identify the biggest conflict + the proposed fix + the ranking upside].\n- *[Client Name B]*: [One-sentence insight: Identify the biggest conflict + the proposed fix + the ranking upside].\n- *[Client Name C]*: [One-sentence insight: Identify the biggest conflict + the proposed fix + the ranking upside].\n\n---\n\ud83d\udca1 *PORTFOLIO STRATEGY NOTE*:\n[A single sentence identifying a common theme across all clients, such as \"Blog-to-Service cannibalization is a recurring trend this week, requiring a global audit of internal linking structures.\"]" }, "promptType": "define", "hasOutputParser": true }, "typeVersion": 3.1 }, { "id": "1d746647-ea83-4f80-99d1-6eaa358ac893", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [ -1568, 496 ], "parameters": { "color": 7, "width": 696, "height": 540, "content": "## 1. Weekly Client Data Setup\nRuns every week, loads the client list, and processes each client one by one through the loop." }, "typeVersion": 1 }, { "id": "f8dea44f-a8ba-4fe4-a8d4-9bb4cdb88731", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [ -848, 496 ], "parameters": { "color": 7, "width": 536, "height": 532, "content": "## 2. Databox MCP - Google Search Console Data\nPulls impressions and average position data from Google Search Console, then merges the SEO performance data for analysis." }, "typeVersion": 1 }, { "id": "0db412fe-9d12-4292-8c1f-98005aba83be", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [ -288, 496 ], "parameters": { "color": 7, "width": 1148, "height": 532, "content": "## 3. Client-Level Cannibalization Check\nCleans and prepares the SEO data, then AI checks if pages are competing against each other in Google search results." }, "typeVersion": 1 }, { "id": "cd236709-4fe0-4e9b-930a-187d9cba5308", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [ -928, -48 ], "parameters": { "color": 7, "width": 972, "height": 460, "content": "## 4. Cross-Client Leadership Report\nAfter all clients are processed, AI creates a combined SEO risk report and sends the final summary to Slack." }, "typeVersion": 1 }, { "id": "850021d1-412c-4218-b185-71ce6b2c47c6", "name": "Send Cannibalization Alert", "type": "n8n-nodes-base.slack", "position": [ 592, 704 ], "parameters": { "text": "={{ $json.output }}", "user": { "__rl": true, "mode": "list", "value": "U0AMDGTLHSN", "cachedResultName": "m.mateja003" }, "select": "user", "otherOptions": { "includeLinkToWorkflow": false } }, "credentials": { "slackApi": { "name": "" } }, "typeVersion": 2.4 }, { "id": "edc60f59-3118-4143-81ac-4975d1a142b3", "name": "Send Cannibalization Alert2", "type": "n8n-nodes-base.slack", "position": [ -224, 80 ], "parameters": { "text": "={{ $json.output }}", "select": "channel", "channelId": { "__rl": true, "mode": "list", "value": "C0AU77RD3PX", "cachedResultName": "databox-keyword-report" }, "otherOptions": { "includeLinkToWorkflow": false } }, "credentials": { "slackApi": { "name": "" } }, "typeVersion": 2.4 }, { "id": "0146ca8a-20b8-4c5d-a045-26c217eb2ad9", "name": "Combine data", "type": "n8n-nodes-base.code", "position": [ 16, 704 ], "parameters": { "jsCode": "// 1. Extract the two datasets from the merged content\n// impressions are in index 0, positions are in index 1\nconst impressionsList = $json.content[0][0].text.results[0].data_points;\nconst positionsList = $json.content[1][0].text.results[0].data_points;\n\nconst urlMap = {};\n\n// 2. Map Impressions by URL\nimpressionsList.forEach(item => {\n const url = item.dimension_values[0].value;\n urlMap[url] = {\n url: url,\n impressions: item.value,\n avgPosition: null\n };\n});\n\n// 3. Join Positions to the Map\npositionsList.forEach(item => {\n const url = item.dimension_values[0].value;\n const position = parseFloat(item.value.toFixed(2));\n \n if (urlMap[url]) {\n urlMap[url].avgPosition = position;\n } else {\n // URL exists in position data but not impressions (rare but possible)\n urlMap[url] = {\n url: url,\n impressions: 0,\n avgPosition: position\n };\n }\n});\n\n// 4. Convert to array and sort by importance (high impressions)\nconst combinedResults = Object.values(urlMap)\n .filter(page => page.impressions > 5) // Filter out low-traffic noise\n .sort((a, b) => b.impressions - a.impressions);\n\nreturn {\n total_pages_analyzed: combinedResults.length,\n seo_summary: combinedResults\n};" }, "typeVersion": 2 }, { "id": "2138fbc6-6623-49d3-829d-f5d75902a5e0", "name": "Aggregate", "type": "n8n-nodes-base.aggregate", "position": [ -208, 704 ], "parameters": { "options": {}, "fieldsToAggregate": { "fieldToAggregate": [ { "fieldToAggregate": "content" } ] } }, "typeVersion": 1 }, { "id": "56fb0bd3-49ac-4eed-89fe-2cc86c213149", "name": "Merge", "type": "n8n-nodes-base.merge", "position": [ -464, 704 ], "parameters": {}, "typeVersion": 3.2 } ], "active": false, "settings": { "availableInMCP": false, "executionOrder": "v1" }, "versionId": "d464827a-c9a3-492c-8d2a-ec788f6d8061", "connections": { "Merge": { "main": [ [ { "node": "Aggregate", "type": "main", "index": 0 } ] ] }, "Aggregate": { "main": [ [ { "node": "Combine data", "type": "main", "index": 0 } ] ] }, "Aggregate3": { "main": [ [ { "node": "SEO Keyword Cannibalization Detector 2", "type": "main", "index": 0 } ] ] }, "Combine data": { "main": [ [ { "node": "SEO Keyword Cannibalization Detector", "type": "main", "index": 0 } ] ] }, "GSC position": { "main": [ [ { "node": "Merge", "type": "main", "index": 1 } ] ] }, "GPT-4o Model2": { "ai_languageModel": [ [ { "node": "SEO Keyword Cannibalization Detector", "type": "ai_languageModel", "index": 0 } ] ] }, "GSC impressions": { "main": [ [ { "node": "Merge", "type": "main", "index": 0 } ] ] }, "Loop Over Items": { "main": [ [ { "node": "Aggregate3", "type": "main", "index": 0 } ], [ { "node": "GSC impressions", "type": "main", "index": 0 }, { "node": "GSC position", "type": "main", "index": 0 } ] ] }, "Set client data": { "main": [ [ { "node": "Loop Over Items", "type": "main", "index": 0 } ] ] }, "OpenAI Chat Model1": { "ai_languageModel": [ [ { "node": "SEO Keyword Cannibalization Detector 2", "type": "ai_languageModel", "index": 0 } ] ] }, "Weekly SEO Monitor": { "main": [ [ { "node": "Set client data", "type": "main", "index": 0 } ] ] }, "Send Cannibalization Alert": { "main": [ [ { "node": "Loop Over Items", "type": "main", "index": 0 } ] ] }, "SEO Keyword Cannibalization Detector": { "main": [ [ { "node": "Send Cannibalization Alert", "type": "main", "index": 0 } ] ] }, "SEO Keyword Cannibalization Detector 2": { "main": [ [ { "node": "Send Cannibalization Alert2", "type": "main", "index": 0 } ] ] } } }