AI-Powered Research Assistant for Platform Questions with GPT-4o and MCP

Anfänger

Dies ist ein AI-Bereich Automatisierungsworkflow mit 5 Nodes. Hauptsächlich werden McpClientTool, Agent, ChatTrigger, LmChatOpenAi und andere Nodes verwendet, kombiniert mit KI-Technologie für intelligente Automatisierung.

Voraussetzungen
  • OpenAI API Key
Workflow-Vorschau
Visualisierung der Node-Verbindungen, mit Zoom und Pan
Workflow exportieren
Kopieren Sie die folgende JSON-Konfiguration und importieren Sie sie in n8n
{
  "meta": {
    "instanceId": "02e782574ebb30fbddb2c3fd832c946466d718819d25f6fe4b920124ff3fc2c1",
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "bc58bd73-921a-445c-a905-6f1bbbc0e9c3",
      "name": "Bei Empfang einer Chat-Nachricht",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        1160,
        420
      ],
      "webhookId": "cf762550-98e7-42f0-a0f3-cd9594331c00",
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "308aea70-2831-4abd-90f6-d4cbf3901be4",
      "name": "n8n Research KI-Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        1440,
        420
      ],
      "parameters": {
        "options": {
          "systemMessage": "You are an assistant integrated with the n8n Multi-Channel Platform (MCP). Your primary role is to interact with the MCP to retrieve available tools and content based on user queries about n8n. When a user asks for information or assistance regarding n8n, first send a request to the MCP to fetch the relevant tools and content. Analyze the retrieved data to understand the available options, then create a tailored response that addresses their specific needs regarding n8n functionalities, documentation, forum posts, or example workflows. Ensure that your responses are clear, actionable, and directly related to the user's queries about n8n."
        }
      },
      "typeVersion": 1.8
    },
    {
      "id": "94cb78f5-3520-4432-b3c9-0524411113e9",
      "name": "n8n-assistant Werkzeug Lookup",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        1500,
        640
      ],
      "parameters": {},
      "credentials": {
        "mcpClientApi": {
          "id": "w1ZOoPXYGz6W2g1T",
          "name": "n8n-assistant"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "78a87949-afda-4c52-ae9f-f8d343fb6567",
      "name": "n8n-assistant Execute Werkzeug",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        1700,
        640
      ],
      "parameters": {
        "toolName": "={{$fromAI(\"tool\",\"Set this specific tool name\")}}",
        "operation": "executeTool",
        "toolParameters": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Tool_Parameters', ``, 'json') }}"
      },
      "credentials": {
        "mcpClientApi": {
          "id": "w1ZOoPXYGz6W2g1T",
          "name": "n8n-assistant"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "cc1619ec-6f49-45e6-8a7b-440da7ee5bc5",
      "name": "OpenAI-Chat-Modell2",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        1320,
        640
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4o-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "id": "q2i0xAiFxUOYOlJ0",
          "name": "OpenAI_BCP"
        }
      },
      "typeVersion": 1.2
    }
  ],
  "pinData": {},
  "connections": {
    "OpenAI Chat Model2": {
      "ai_languageModel": [
        [
          {
            "node": "n8n Research AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "n8n-assistant Tool Lookup": {
      "ai_tool": [
        [
          {
            "node": "n8n Research AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "bc58bd73-921a-445c-a905-6f1bbbc0e9c3": {
      "main": [
        [
          {
            "node": "n8n Research AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "n8n-assistant Execute Tool": {
      "ai_tool": [
        [
          {
            "node": "n8n Research AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    }
  }
}
Häufig gestellte Fragen

Wie verwende ich diesen Workflow?

Kopieren Sie den obigen JSON-Code, erstellen Sie einen neuen Workflow in Ihrer n8n-Instanz und wählen Sie "Aus JSON importieren". Fügen Sie die Konfiguration ein und passen Sie die Anmeldedaten nach Bedarf an.

Für welche Szenarien ist dieser Workflow geeignet?

Anfänger - Künstliche Intelligenz

Ist es kostenpflichtig?

Dieser Workflow ist völlig kostenlos. Beachten Sie jedoch, dass Drittanbieterdienste (wie OpenAI API), die im Workflow verwendet werden, möglicherweise kostenpflichtig sind.

Workflow-Informationen
Schwierigkeitsgrad
Anfänger
Anzahl der Nodes5
Kategorie1
Node-Typen4
Schwierigkeitsbeschreibung

Für n8n-Anfänger, einfache Workflows mit 1-5 Nodes

Autor

Hello, I'm Onur I've been working as a freelance software developer for about four years. In addition, I develop my own projects. For some time, I have been improving myself and providing various services related to AI and AI workflows. Both by writing low code and code. If you have any questions, don't hesitate to contact me.

Externe Links
Auf n8n.io ansehen

Diesen Workflow teilen

Kategorien

Kategorien: 34