AI Explainer Webhook with Claude API

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": "SecureHeaders - 03 AI Explainer",
  "nodes": [
    {
      "parameters": {
        "httpMethod": "POST",
        "path": "explain-headers",
        "responseMode": "responseNode",
        "options": {}
      },
      "id": "c1b2c3d4-0001-0001-0001-000000000001",
      "name": "Webhook",
      "type": "n8n-nodes-base.webhook",
      "typeVersion": 2,
      "position": [
        0,
        0
      ]
    },
    {
      "parameters": {
        "jsCode": "const scan = $input.first().json.body;\nconst url = scan.url || 'unknown';\nconst score = scan.score || 0;\nconst grade = scan.grade || 'F';\nconst headers = scan.headers || [];\n\nconst missingHeaders = headers.filter(h => !h.present);\nconst passingHeaders = headers.filter(h => h.present);\n\nconst missingList = missingHeaders.map(h => `- ${h.header}: ${h.description}`).join('\\n');\nconst passingList = passingHeaders.map(h => `- ${h.header}`).join('\\n');\n\nconst prompt = `You are a cybersecurity expert. Analyze this website's security header scan and give a concise, friendly report.\n\nWebsite: ${url}\nSecurity Score: ${score}/100 (Grade: ${grade})\n\nMISSING headers (security risks):\n${missingList || 'None'}\n\nPRESENT headers (good):\n${passingList || 'None'}\n\nProvide:\n1. A 2-sentence plain-English summary of the security risk level\n2. Top 3 priority fixes (most critical first) with a one-line explanation of WHY each matters\n3. One positive thing if any headers are present\n\nKeep it under 200 words. Be direct and developer-friendly.`;\n\nreturn [{ json: { prompt, url, score, grade } }];"
      },
      "id": "c1b2c3d4-0002-0002-0002-000000000002",
      "name": "Build Prompt",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        240,
        0
      ]
    },
    {
      "parameters": {
        "method": "POST",
        "url": "https://api.anthropic.com/v1/messages",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
            {
              "name": "anthropic-version",
              "value": "2023-06-01"
            }
          ]
        },
        "sendBody": true,
        "specifyBody": "json",
        "jsonBody": "={\n  \"model\": \"claude-haiku-4-5-20251001\",\n  \"max_tokens\": 400,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": {{ JSON.stringify($json.prompt) }}\n    }\n  ]\n}",
        "options": {}
      },
      "id": "c1b2c3d4-0003-0003-0003-000000000003",
      "name": "Call Claude API",
      "type": "n8n-nodes-base.httpRequest",
      "typeVersion": 4.2,
      "position": [
        480,
        0
      ],
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      }
    },
    {
      "parameters": {
        "jsCode": "const claudeResponse = $input.first().json;\nconst prevData = $('Build Prompt').first().json;\n\nconst explanation = claudeResponse.content?.[0]?.text || 'Unable to generate explanation.';\n\nreturn [{\n  json: {\n    url: prevData.url,\n    score: prevData.score,\n    grade: prevData.grade,\n    explanation\n  }\n}];"
      },
      "id": "c1b2c3d4-0004-0004-0004-000000000004",
      "name": "Extract Response",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        720,
        0
      ]
    },
    {
      "parameters": {
        "respondWith": "json",
        "responseBody": "={{ JSON.stringify($json) }}",
        "options": {
          "responseHeaders": {
            "entries": [
              {
                "name": "Access-Control-Allow-Origin",
                "value": "*"
              },
              {
                "name": "Content-Type",
                "value": "application/json"
              }
            ]
          }
        }
      },
      "id": "c1b2c3d4-0005-0005-0005-000000000005",
      "name": "Respond to Webhook",
      "type": "n8n-nodes-base.respondToWebhook",
      "typeVersion": 1.1,
      "position": [
        960,
        0
      ]
    }
  ],
  "connections": {
    "Webhook": {
      "main": [
        [
          {
            "node": "Build Prompt",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Build Prompt": {
      "main": [
        [
          {
            "node": "Call Claude API",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Call Claude API": {
      "main": [
        [
          {
            "node": "Extract Response",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Extract Response": {
      "main": [
        [
          {
            "node": "Respond to Webhook",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  }
}

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.

• httpHeaderAuth

About this workflow

SecureHeaders - 03 AI Explainer. Uses httpRequest. Webhook trigger; 5 nodes.

Source: https://github.com/Arryn21/header-security-project/blob/b411fbbf7768c98ed76de71a7490aa7fe6d07dd9/n8n-workflows/03-ai-explainer.json — original creator credit. Request a take-down →

More Web Scraping workflows → · Browse all categories →

Related workflows

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