AI Knowledge Agent Chatbot

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": "KnowledgeAgent",
  "nodes": [
    {
      "parameters": {
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.4,
      "position": [
        -176,
        -32
      ],
      "id": "e2ec9377-4ec6-49ca-a12d-b960beea55e9",
      "name": "When chat message received"
    },
    {
      "parameters": {
        "options": {
          "systemMessage": "You are a research assistant. Analyze input data and provide reports. You have access to the Tavily search and Tavily extract MCP tools. Use these to obtain the latest news and developments. Use Tavily Search no more than 2 times and Tavily Extract no more than 2 times\n\nFind the latest development using the Tavily search and find more information using the Tavily Extract tool. Finally produce an executive level summary report from your findings. This can be no more than 1000 words with the Executive Summary at the front of the report being no more than 50 words.\n"
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 3.1,
      "position": [
        96,
        -128
      ],
      "id": "bf03356c-82b0-4296-9f8b-dc3be5b8e1a0",
      "name": "AI Agent"
    },
    {
      "parameters": {
        "endpointUrl": "https://mcp.tavily.com/mcp/?tavilyApiKey=tvly-dev-REDACTED",
        "authentication": "headerAuth",
        "include": "selected",
        "includeTools": [
          "tavily_extract"
        ],
        "options": {
          "timeout": 60000
        }
      },
      "type": "@n8n/n8n-nodes-langchain.mcpClientTool",
      "typeVersion": 1.2,
      "position": [
        464,
        32
      ],
      "id": "f15db6cd-e646-43d0-b293-a0f0c910cd5d",
      "name": "Tavily Extract"
    },
    {
      "parameters": {
        "endpointUrl": "https://mcp.tavily.com/mcp/?tavilyApiKey=tvly-dev-REDACTED",
        "authentication": "headerAuth",
        "include": "selected",
        "includeTools": [
          "tavily_search"
        ],
        "options": {
          "timeout": 60000
        }
      },
      "type": "@n8n/n8n-nodes-langchain.mcpClientTool",
      "typeVersion": 1.2,
      "position": [
        336,
        80
      ],
      "id": "c5e3b5ec-5880-4d9a-8cce-f24f674da5ac",
      "name": "Tavily Search"
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "claude-opus-4-5-20251101",
          "mode": "list",
          "cachedResultName": "Claude Opus 4.5"
        },
        "options": {
          "maxTokensToSample": 1500
        }
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatAnthropic",
      "typeVersion": 1.3,
      "position": [
        -16,
        112
      ],
      "id": "52d954ea-4479-4477-88e5-68912b8c7d1e",
      "name": "Anthropic Chat Model"
    },
    {
      "parameters": {
        "workflowInputs": {
          "values": [
            {
              "name": "chatInput"
            }
          ]
        }
      },
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "typeVersion": 1.1,
      "position": [
        -144,
        -240
      ],
      "id": "11dc1f68-b030-4be7-8fe2-9325f69ec510",
      "name": "When Executed by Another Workflow"
    }
  ],
  "connections": {
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Tavily Extract": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Tavily Search": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Anthropic Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "When Executed by Another Workflow": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": true,
  "settings": {
    "executionOrder": "v1",
    "binaryMode": "separate",
    "availableInMCP": false
  },
  "versionId": "b0601824-22ce-4b21-a9e1-998a7063985f",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "u1iMzuai0rAiUCcS",
  "tags": []
}

About this workflow

KnowledgeAgent. Uses chatTrigger, agent, mcpClientTool, lmChatAnthropic. Chat trigger; 6 nodes.

Source: https://github.com/stevef1uk/artificial_mind/blob/3a31ff1b62797033ffe4c8eb0da369a75c7c83cb/n8n/KnowledgeAgent.json — 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.