AI Assistant Answers Questions with RAG and Search MCP

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": "91f18887-363a-4c6d-9d49-981e05bb52bf",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "position": [
        0,
        0
      ],
      "parameters": {
        "options": {}
      },
      "typeVersion": 1.1
    },
    {
      "id": "7d21346c-f225-4cc8-85d6-6dd68fc9a035",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "position": [
        220,
        0
      ],
      "parameters": {
        "options": {
          "systemMessage": "You are a helpful assistant\n\nYou answer questions about MCP (Model Context Protocol). You have access to two MCP servers:\n\n- The RAG MCP Server which answers general questions about MCP\n- The Search Engine MCP Server which allows you to use a Search Engine in realtime.\n\nThe Search Engine MCP Server has two tools;\n- list tool - which shows all the available tools\n- execute tool - which allows you to execute a search query on a search engine.\n\nYou DO NOT answer questions with your internal knowledge, you ONLY use the knowledge provided by the two MCP servers to answer questions."
        }
      },
      "typeVersion": 2
    },
    {
      "id": "ab24be4f-acbd-47b9-abe1-1db621150971",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        -20,
        280
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-4.1-mini"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    },
    {
      "id": "71e5008a-2e56-4588-a4c3-a8724026b998",
      "name": "Simple Memory",
      "type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
      "position": [
        180,
        280
      ],
      "parameters": {
        "contextWindowLength": 15
      },
      "typeVersion": 1.3
    },
    {
      "id": "aa1ae334-de5d-4cd3-a4a5-60f48ca37bbe",
      "name": "MCP_Search_List_Tools",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        680,
        280
      ],
      "parameters": {},
      "credentials": {
        "mcpClientApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "cef78817-9d96-4e16-80d1-6c8a2e7b574b",
      "name": "Sticky Note",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        320,
        220
      ],
      "parameters": {
        "color": 3,
        "width": 280,
        "height": 220,
        "content": "## RAG MCP Server"
      },
      "typeVersion": 1
    },
    {
      "id": "62d8bad6-50f4-4eec-b553-2107c7e5ee28",
      "name": "Sticky Note1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        620,
        220
      ],
      "parameters": {
        "color": 5,
        "width": 360,
        "height": 220,
        "content": "## Search Engine MCP Server"
      },
      "typeVersion": 1
    },
    {
      "id": "4522cb25-9a05-4509-a3cb-0f4275c95bb3",
      "name": "MCP_Search_Search_Engine",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        860,
        280
      ],
      "parameters": {
        "toolName": "search_engine",
        "operation": "executeTool",
        "toolParameters": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Tool_Parameters', ``, 'json') }}"
      },
      "credentials": {
        "mcpClientApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    },
    {
      "id": "e96335a9-cc8a-4d29-85d2-905321fba47c",
      "name": "RAG MCP Server",
      "type": "@n8n/n8n-nodes-langchain.mcpClientTool",
      "position": [
        420,
        280
      ],
      "parameters": {
        "sseEndpoint": "http://localhost:5678/mcp/f88b9b77-40f2-4fad-8e14-0fc7faed7a0b"
      },
      "typeVersion": 1
    },
    {
      "id": "76531f2c-8f92-455f-a618-8fc1dd579d03",
      "name": "MCP Client",
      "type": "n8n-nodes-mcp.mcpClientTool",
      "position": [
        580,
        220
      ],
      "parameters": {},
      "credentials": {
        "mcpClientApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1
    }
  ],
  "connections": {
    "MCP Client": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Simple Memory": {
      "ai_memory": [
        [
          {
            "node": "AI Agent",
            "type": "ai_memory",
            "index": 0
          }
        ]
      ]
    },
    "RAG MCP Server": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "MCP_Search_List_Tools": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "MCP_Search_Search_Engine": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "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.

• mcpClientApi
• openAiApi

About this workflow

This workflow contains community nodes that are only compatible with the self-hosted version of n8n.

Source: https://n8n.io/workflows/5398/ — 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.