Daily Topic News Digest with Gemini Ai, Decodo Mcp and Slack

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 →

{
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "d342f950-aa50-4cb3-92e1-cb8764552115",
      "name": "Decodo MCP",
      "type": "@n8n/n8n-nodes-langchain.mcpClientTool",
      "position": [
        -224,
        -160
      ],
      "parameters": {
        "options": {},
        "endpointUrl": "https://server.smithery.ai/@Decodo/decodo-mcp-server/mcp?api_key=YOUR_TOKEN_HERE&profile=YOUR_DECODO_PROFILE_ID",
        "serverTransport": "httpStreamable"
      },
      "typeVersion": 1.1
    },
    {
      "id": "c2d6c8f2-0f51-4a5f-877a-390e207b41fe",
      "name": "Split",
      "type": "n8n-nodes-base.splitOut",
      "position": [
        288,
        -416
      ],
      "parameters": {
        "options": {},
        "fieldToSplitOut": "output.items"
      },
      "typeVersion": 1
    },
    {
      "id": "56bb6812-b074-4f22-a677-bd53eb04da86",
      "name": "Slack",
      "type": "n8n-nodes-base.slack",
      "position": [
        1040,
        -416
      ],
      "parameters": {
        "text": "={{\n(() => {\n  // Prefer aggregated array, else fall back to current items\n  const arr = Array.isArray($json.articles) ? $json.articles\n            : ($items && $items.length ? $items.map(i => i.json) : []);\n  if (!arr.length) return \"No fresh items today.\";\n  // Escape for Slack mrkdwn\n  const htmlEsc = s => String(s || '')\n    .replace(/&/g,'&amp;').replace(/</g,'&lt;').replace(/>/g,'&gt;');\n  const mdEsc = s => htmlEsc(s).replace(/([_*~`])/g, '\\\\$1');\n  const domain = u => { try { return new URL(u).hostname.replace(/^www\\./,''); } catch { return ''; } };\n  const parseDate = v => { const d = new Date(v || Date.now()); return isNaN(d) ? new Date() : d; };\n  const toIST = v => {\n    try { return parseDate(v).toLocaleString('en-IN',{ timeZone:'Asia/Kolkata', hour12:false }); }\n    catch { return ''; }\n  };\n  \n  const body = arr\n    .sort((x,y) => new Date(y.date || y?.json?.date || 0) - new Date(x.date || x?.json?.date || 0))\n    .map((it) => {\n      const url = it.url ?? it?.json?.url ?? '';\n      const title = mdEsc(it.title ?? it?.json?.title ?? '(untitled)');\n      const src = (it.source ?? it?.json?.source) || domain(url);\n      const summary = mdEsc(it.summary ?? it?.json?.summary ?? '');\n      const link = url ? `<${url}|${title}>` : title;\n      return `*${link}* (${src})\\n${summary}`;\n    })\n    .join('\\n\\n');\n  return `\\n\\n${body}`;\n})()\n}}",
        "select": "channel",
        "channelId": {
          "__rl": true,
          "mode": "name",
          "value": "#random"
        },
        "otherOptions": {}
      },
      "credentials": {
        "slackApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "e79daa86-feaf-44d4-ac43-d86f42ebbc92",
      "name": "Gemini Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        -368,
        -208
      ],
      "parameters": {
        "options": {}
      },
      "credentials": {
        "googlePalmApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "678b965f-c475-453c-a261-6bc7107072d7",
      "name": "Remove Duplicates",
      "type": "n8n-nodes-base.removeDuplicates",
      "position": [
        496,
        -416
      ],
      "parameters": {
        "compare": "selectedFields",
        "options": {},
        "fieldsToCompare": "url, title"
      },
      "typeVersion": 2
    },
    {
      "id": "d51019dd-248b-4ab7-8237-5af487e8a0e9",
      "name": "Combine Results",
      "type": "n8n-nodes-base.aggregate",
      "position": [
        704,
        -416
      ],
      "parameters": {
        "options": {},
        "aggregate": "aggregateAllItemData",
        "destinationFieldName": "articles"
      },
      "typeVersion": 1
    },
    {
      "id": "9d90b4e7-3498-48f8-836a-476158058251",
      "name": "Set Topics",
      "type": "n8n-nodes-base.set",
      "position": [
        -784,
        -416
      ],
      "parameters": {
        "mode": "raw",
        "options": {
          "dotNotation": false
        },
        "jsonOutput": "{\n  \"topics\": [\n    \"model context protocol (mcp)\",\n    \"generative AI\",\n    \"agentic AI\",\n    \"web scraping\"\n  ]\n}"
      },
      "typeVersion": 3.4
    },
    {
      "id": "85f6c739-446d-4bb2-a0ef-4b927f5d266c",
      "name": "Format Results",
      "type": "n8n-nodes-base.code",
      "position": [
        80,
        -416
      ],
      "parameters": {
        "jsCode": "// Input shape we see sometimes:\n// { output: \"```json\\n[ {...}, {...} ]\\n```\" }  OR plain \"[ {...} ]\"\nlet raw = String($json.output || \"\").trim();\n\n// 1) Strip code fences if present\nraw = raw.replace(/^```(?:json)?\\s*/i, \"\").replace(/```$/, \"\");\n\n// 2) If there is extra chatter, extract the first JSON array\nconst m = raw.match(/\\[[\\s\\S]*\\]/);\nconst arrayText = m ? m[0] : \"[]\";\n\n// 3) Parse safely (with a trailing-comma fix fallback)\nlet arr;\ntry {\n  arr = JSON.parse(arrayText);\n} catch {\n  const fixed = arrayText.replace(/,\\s*([\\]}])/g, \"$1\");\n  try { \n    arr = JSON.parse(fixed); \n  } catch { \n    arr = []; \n  }\n}\n\n// 4) Normalize minimal fields so downstream is predictable\nconst domainFrom = (u) => { \n  try { \n    return new URL(u).hostname.replace(/^www\\./, \"\"); \n  } catch { \n    return \"\"; \n  } \n};\n\nconst items = (Array.isArray(arr) ? arr : []).map(x => ({\n  title: String(x?.title || \"\").trim(),\n  url: String(x?.url || \"\").trim(),\n  source: domainFrom(x?.url) || String(x?.source || \"\").trim(),\n  date: x?.date || new Date().toISOString(),\n  topic: String(x?.topic || \"\").trim(),\n  summary: String(x?.summary || \"\").trim(),\n}));\n\n// 5) Return clean structure\nreturn { json: { output: { items } } };"
      },
      "typeVersion": 2
    },
    {
      "id": "03ce55b1-a1b5-4e25-8258-cc2eb19858c2",
      "name": "Schedule Trigger",
      "type": "n8n-nodes-base.scheduleTrigger",
      "position": [
        -1008,
        -416
      ],
      "parameters": {
        "rule": {
          "interval": [
            {
              "triggerAtHour": 9
            }
          ]
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "9dd80e81-03e3-4f51-864f-b6fbe4ef3de3",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1056,
        -528
      ],
      "parameters": {
        "color": 7,
        "width": 486,
        "height": 272,
        "content": "## \u23f0 DAILY TRIGGER & TOPICS\nRuns at 9 AM with predefined search topics (AI, MCP, web scraping)\n"
      },
      "typeVersion": 1
    },
    {
      "id": "316f4a7f-70b1-46b7-bcd7-0d91edc99445",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -512,
        -528
      ],
      "parameters": {
        "width": 496,
        "height": 496,
        "content": "## \ud83e\udd16 SMART NEWS AGENT\nAI finds fresh news using [**Decodo MCP**](https://github.com/Decodo/mcp-web-scraper) web scraping tools and Gemini to search and extract articles from last 48 hours."
      },
      "typeVersion": 1
    },
    {
      "id": "63739468-1318-4306-b161-9660c5148330",
      "name": "Agent: News Finder",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "maxTries": 2,
      "position": [
        -368,
        -416
      ],
      "parameters": {
        "text": "=You are a news scout. Topics: {{$json.topics}}.\nGoal: For each topic, use the Decodo MCP tools available to you to find fresh, high-quality news from the last 48 hours, extract essentials, and list concise candidates.\n\nRules:\n- Use only tools exposed via Decodo MCP.\n- Prefer official/reputable sources; avoid spam and duplicates (same URL or same title).\n- Up to 5 items per topic, newest first.\n- Provide for each item: title, url, topic, (optional) source domain, publish date/time if available, 2\u20133 line plain-text summary.\n- If nothing relevant is found for a topic, skip it.\n\nOutput format for THIS STEP ONLY:\nReturn a JSON array of candidate objects, one per item (not wrapped in any parent object), e.g.:\n[\n  {\"title\":\"...\", \"url\":\"https://...\", \"topic\":\"...\", \"source\":\"example.com\", \"date\":\"2025-09-15T09:00:00Z\", \"summary\":\"...\"}\n]\n\nDo not include any markdown or commentary\u2014just the JSON array.",
        "options": {},
        "promptType": "define"
      },
      "executeOnce": false,
      "retryOnFail": false,
      "typeVersion": 2.2,
      "alwaysOutputData": false
    },
    {
      "id": "66c231a2-cf5a-4d24-b883-b24fb77114bb",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        48,
        -528
      ],
      "parameters": {
        "color": 7,
        "width": 784,
        "height": 496,
        "content": "## \ud83d\udd27 CLEAN & ORGANIZE\nFormat messy data \u2192 Split articles \u2192 Remove duplicates \u2192 Combine final list"
      },
      "typeVersion": 1
    },
    {
      "id": "08047e22-607d-47fb-9963-bc4617e766f6",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        896,
        -528
      ],
      "parameters": {
        "color": 7,
        "width": 464,
        "height": 496,
        "content": "## \ud83d\udcf1 SEND TO SLACK\nDelivers clean news digest with clickable links and summaries\n"
      },
      "typeVersion": 1
    },
    {
      "id": "9e6989ca-dd0f-4780-9081-658e593e3a19",
      "name": "Sticky Note4",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1776,
        -800
      ],
      "parameters": {
        "width": 608,
        "height": 864,
        "content": "## Try It Out!\n**This n8n template demonstrates how to build an autonomous AI news agent using Decodo MCP that automatically finds, scrapes, and delivers fresh industry news to your team via Slack.** \n\nUse cases are many \u2013 automated news monitoring for your industry, competitive intelligence gathering, startup monitoring, regulatory updates, research automation, or daily briefings for your organization.\n\n### How it works\n- Define your news topics using the Set node \u2013 AI, MCP, web scraping, whatever matters to your business.\n- The AI Agent processes those topics using Gemini Chat Model, determining which tools to use and when.\n- Here's where it gets interesting: [Decodo MCP](https://github.com/Decodo/mcp-web-scraper) gives your AI agent the tools to search Google, scrape websites, and parse content automatically \u2013 all while bypassing geo-restrictions and anti-bot measures.\n- The agent hunts for fresh articles from the last 48 hours, extracts clean data, and returns structured JSON results.\n- Format Results cleans up the AI's messy output and removes duplicates.\n- Your polished news digest gets delivered to Slack with clickable links and summaries.\n\n### How to use\n- Schedule trigger runs daily at 9 AM \u2013 adjust timing as needed.\n- Customize topics in the Set node to match your industry.\n- Scales effortlessly: add more topics, tweak search criteria, done.\n\n### Requirements\n- [Decodo MCP credentials](https://decodo.com/blog/how-to-set-up-mcp-server) ([grab the free trial](https://dashboard.decodo.com/) today).\n- [Gemini API key](https://aistudio.google.com/app/apikey) for AI processing.\n- [Slack workspace](https://docs.n8n.io/integrations/builtin/app-nodes/n8n-nodes-base.slack/) for news delivery.\n\n### Need help?\nJoin the [Discord](https://discord.com/invite/gvJhWJPaB4) or email [support@decodo.com](mailto:support@decodo.com) for questions.\n\nHappy Automating!"
      },
      "typeVersion": 1
    }
  ],
  "connections": {
    "Slack": {
      "main": [
        []
      ]
    },
    "Split": {
      "main": [
        [
          {
            "node": "Remove Duplicates",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Decodo MCP": {
      "ai_tool": [
        [
          {
            "node": "Agent: News Finder",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Set Topics": {
      "main": [
        [
          {
            "node": "Agent: News Finder",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Format Results": {
      "main": [
        [
          {
            "node": "Split",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Combine Results": {
      "main": [
        [
          {
            "node": "Slack",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Schedule Trigger": {
      "main": [
        [
          {
            "node": "Set Topics",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Gemini Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "Agent: News Finder",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Remove Duplicates": {
      "main": [
        [
          {
            "node": "Combine Results",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Agent: News Finder": {
      "main": [
        [
          {
            "node": "Format Results",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• googlePalmApi
• slackApi

About this workflow

This n8n template demonstrates how to build an autonomous AI news agent using Decodo MCP that automatically finds, scrapes, and delivers fresh industry news to your team via Slack.

Source: https://n8n.io/workflows/8738/ — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.