{
  "name": "Scrape Web Data with Bright Data, Google Gemini and MCP Automated AI Agent",
  "nodes": [
    {
      "id": "0c747f5b-ef72-4e00-a028-4a08461dae28",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "notes": "Bright Data Web Scraping Agent",
      "position": [
        -140,
        60
      ],
      "parameters": {
        "text": "=Scrape the web data as per the provided URL:  {{ $json.url }} using the format as {{ $json.format }}",
        "options": {
          "systemMessage": "=You are a helpful assistant."
        },
        "promptType": "define"
      },
      "notesInFlow": true,
      "typeVersion": 1.8
    },
    {
      "id": "16c7cd90-39da-47a4-8020-a0aa8f87275a",
      "name": "When clicking ‘Test workflow’",
      "type": "n8n-nodes-base.manualTrigger",
      "position": [
        -640,
        -300
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "7b544505-6b6b-4500-a2ad-f7cf62f98c13",
      "name": "MCP Client list all tools for Bright Data",
      "type": "n8n-nodes-mcp.mcpClient",
      "position": [
        -380,
        -300
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "9f5bf319-9414-4974-bad2-ea24f09ae351",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -220,
        -400
      ],
      "parameters": {
        "color": 3,
        "width": 440,
        "height": 320,
        "content": "## Bright Data Web Scraper"
      },
      "typeVersion": 1
    },
    {
      "id": "222e81cf-878e-42de-a325-6b6659145f98",
      "name": "MCP Client List all tools",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        440,
        420
      ],
      "parameters": {},
      "typeVersion": 1
    },
    {
      "id": "a10dfd4f-cadf-4952-8449-1865406358d4",
      "name": "MCP Client Bright Data Web Scraper",
      "type": "n8n-nodes-mcp.mcpClient",
      "notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.",
      "position": [
        60,
        -300
      ],
      "parameters": {
        "toolName": "=scrape_as_markdown",
        "operation": "executeTool",
        "toolParameters": "={\n   \"url\": \"{{ $json.url }}\"\n} "
      },
      "notesInFlow": true,
      "typeVersion": 1
    },
    {
      "id": "0acbd4ff-ce4a-4ff2-b213-2d80dd91e302",
      "name": "Webhook for web scraper",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        280,
        -300
      ],
      "parameters": {
        "url": "=https://webhook.site/daf9d591-a130-4010-b1d3-0c66f8fcf467",
        "options": {},
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "response",
              "value": "={{ $json.result.content[0].text }}"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "009ac29f-8cad-4b58-9ca4-e75470a52dcc",
      "name": "Set the URLs",
      "type": "n8n-nodes-base.set",
      "position": [
        -160,
        -300
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "214e61a0-3587-453f-baf5-eac013990857",
              "name": "url",
              "type": "string",
              "value": "https://about.google/"
            },
            {
              "id": "45014942-0a2e-4f46-b395-f82f97bfa93e",
              "name": "webhook_url",
              "type": "string",
              "value": "https://webhook.site/ce41e056-c097-48c8-a096-9b876d3abbf7"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "104706dd-ae58-47fd-8fea-cefa986ae40c",
      "name": "MCP Client to Scrape as Markdown",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.",
      "position": [
        -60,
        400
      ],
      "parameters": {
        "toolName": "scrape_as_markdown",
        "operation": "executeTool",
        "toolParameters": "={\n  \"url\": \"{{ $json.url }}\"\n} ",
        "descriptionType": "manual",
        "toolDescription": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language."
      },
      "notesInFlow": false,
      "typeVersion": 1
    },
    {
      "id": "c03c655e-45c8-4278-a01f-ba48282459c5",
      "name": "MCP Client to Scrape as HTML",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in HTML.",
      "position": [
        200,
        400
      ],
      "parameters": {
        "toolName": "scrape_as_html",
        "operation": "executeTool",
        "toolParameters": "{\n  \"url\": \"{{ $json.url }}\"\n} ",
        "descriptionType": "manual",
        "toolDescription": "Scrape a single webpage URL with advanced options for content extraction and get back the results in HTML."
      },
      "notesInFlow": true,
      "typeVersion": 1
    },
    {
      "id": "587300ff-44e5-4ff2-9dee-a4f8720ca26b",
      "name": "Google Gemini Chat Model for AI Agent",
      "type": "@n8n/n8n-nodes-langchain.lmChatGoogleGemini",
      "position": [
        -520,
        400
      ],
      "parameters": {
        "options": {},
        "modelName": "models/gemini-2.0-flash-exp"
      },
      "typeVersion": 1
    },
    {
      "id": "38ba13a1-f8f7-48ce-a05d-2c2526de606d",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -140,
        340
      ],
      "parameters": {
        "color": 4,
        "width": 480,
        "height": 260,
        "content": "## Bright Data Web Scraper Tools"
      },
      "typeVersion": 1
    },
    {
      "id": "e7c8d333-e256-4944-a584-575162072ca4",
      "name": "Simple Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        -280,
        400
      ],
      "parameters": {
        "sessionKey": "=Perform the web scraping for the below URL\n\n{{ $json.url }}",
        "sessionIdType": "customKey",
        "contextWindowLength": 10
      },
      "typeVersion": 1.3
    },
    {
      "id": "5e89519e-8ee5-4c3b-807d-21cef6e36c32",
      "name": "Webhook for Web Scraper AI Agent",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        260,
        120
      ],
      "parameters": {
        "url": "={{ $('Set the URL with the Webhook URL and data format').item.json.webhook_url }}",
        "options": {},
        "sendBody": true,
        "bodyParameters": {
          "parameters": [
            {
              "name": "response",
              "value": "={{ $json.output }}"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "2de093f4-15e5-4710-83d9-e6d9ed852873",
      "name": "Set the URL with the Webhook URL and data format",
      "type": "n8n-nodes-base.set",
      "position": [
        -400,
        60
      ],
      "parameters": {
        "options": {},
        "assignments": {
          "assignments": [
            {
              "id": "214e61a0-3587-453f-baf5-eac013990857",
              "name": "url",
              "type": "string",
              "value": "https://about.google/"
            },
            {
              "id": "45014942-0a2e-4f46-b395-f82f97bfa93e",
              "name": "webhook_url",
              "type": "string",
              "value": "https://webhook.site/daf9d591-a130-4010-b1d3-0c66f8fcf467"
            },
            {
              "id": "7f6c03f6-9fa3-45f9-bf81-243b7106bdac",
              "name": "format",
              "type": "string",
              "value": "scrape_as_markdown"
            }
          ]
        }
      },
      "typeVersion": 3.4
    },
    {
      "id": "04a5b11f-1990-440e-be23-2fbcb985dd4a",
      "name": "Create a binary data",
      "type": "n8n-nodes-base.function",
      "position": [
        260,
        -80
      ],
      "parameters": {
        "functionCode": "items[0].binary = {\n  data: {\n    data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n  }\n};\nreturn items;"
      },
      "typeVersion": 1
    },
    {
      "id": "0765ffcd-4746-45f7-add8-f82d66709321",
      "name": "Write the scraped content to disk",
      "type": "n8n-nodes-base.readWriteFile",
      "position": [
        460,
        -80
      ],
      "parameters": {
        "options": {},
        "fileName": "d:\\Scraped-Content.json",
        "operation": "write"
      },
      "typeVersion": 1
    },
    {
      "id": "16cd9b48-765d-4f0d-8e78-6c41cfc50b03",
      "name": "Sticky Note2",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -220,
        -540
      ],
      "parameters": {
        "width": 440,
        "height": 120,
        "content": "## Disclaimer\nThis template is only available on n8n self-hosted as it's making use of the community node for MCP Client."
      },
      "typeVersion": 1
    },
    {
      "id": "ff4b9e9c-a0f0-4cdb-ad53-55dc412794fc",
      "name": "Sticky Note3",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        -1080,
        -80
      ],
      "parameters": {
        "color": 5,
        "width": 480,
        "height": 380,
        "content": "## Note\nThe AI agent utilizes Bright Data's MCP tools to perform web scraping based on user requests. It intelligently selects the most suitable web scraping tool to fulfill the user's query.\n\nOnce the web scraping is complete, the AI agent's response is:\n\n1. Used to trigger a webhook call.\n\n2. Persisted to disk for future reference.\n\nGoogle Gemini is employed by the AI agent to understand and interpret user queries. Based on this interpretation, the agent initiates a call to the appropriate MCP client to perform the required web scraping task.\n\nSource - https://github.com/luminati-io/brightdata-mcp"
      },
      "typeVersion": 1
    },
    {
      "id": "17ab05d1-7684-5caa-b0fa-f87e4f6979ea",
      "name": "Publication · Overview and setup",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -1880,
        -540
      ],
      "parameters": {
        "content": "# Scrape Web Data with Bright Data, Google Gemini and MCP Automated AI Agent\n\n## Purpose and structure\nThis folder contains the **Scrape Web Data with Bright Data, Google Gemini and MCP Automated AI Agent** workflow. Its executable nodes use `agent`, `function`, `httpRequest`, `lmChatGoogleGemini`, `manualTrigger`, `mcpClient`, `mcpClientTool`, `memoryBufferWindow`, `readWriteFile`, `set`. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.\n\n## Setup\nImport inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.\n\n## Entry points\nWhen clicking ‘Test workflow’\n\n## Verification\nSanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.\n\n## Attribution\nhttps://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Manual/1707_Manual_Stickynote_Automate_Webhook.json\nMIT; preserve source notices.",
        "width": 700,
        "height": 800,
        "color": 1
      }
    }
  ],
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "connections": {
    "AI Agent": {
      "main": [
        [
          {
            "node": "Webhook for Web Scraper AI Agent",
            "type": "main",
            "index": 0
          },
          {
            "node": "Create a binary data",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set the URLs": {
      "main": [
        [
          {
            "node": "MCP Client Bright Data Web Scraper",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "Create a binary data": {
      "main": [
        [
          {
            "node": "Write the scraped content to disk",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "MCP Client List all tools": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "MCP Client to Scrape as HTML": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "MCP Client to Scrape as Markdown": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Webhook for Web Scraper AI Agent": {
      "main": [
        []
      ]
    },
    "When clicking ‘Test workflow’": {
      "main": [
        [
          {
            "node": "MCP Client list all tools for Bright Data",
            "type": "main",
            "index": 0
          },
          {
            "node": "Set the URL with the Webhook URL and data format",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "MCP Client Bright Data Web Scraper": {
      "main": [
        [
          {
            "node": "Webhook for web scraper",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Google Gemini Chat Model for AI Agent": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "MCP Client list all tools for Bright Data": {
      "main": [
        [
          {
            "node": "Set the URLs",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Set the URL with the Webhook URL and data format": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}