This workflow follows the Agent → Chat Trigger recipe pattern — see all workflows that pair these two integrations.
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 →
{
"id": "6MRJ2tfl8c2f3AuE",
"name": "\ud83d\udca5\ud83d\udee0\ufe0fBuild a Web Search Chatbot with GPT-4o and MCP Brave Search",
"tags": [],
"nodes": [
{
"id": "b6e5eaa8-ddb3-4c13-8069-ce360bf4a945",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
240,
-180
],
"parameters": {
"options": {}
},
"typeVersion": 1.8
},
{
"id": "dde0154e-f7c2-4778-abcc-f79406db5e6b",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-260,
-180
],
"parameters": {
"options": {}
},
"typeVersion": 1.1
},
{
"id": "877ce640-4d08-4ba7-b1d3-bcfc79600d2c",
"name": "MCP Get Brave Tools",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
200,
280
],
"parameters": {},
"credentials": {
"mcpClientApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "fb3ce3c2-a809-43e5-92d0-82db0d78a971",
"name": "MCP Execute Brave Search",
"type": "n8n-nodes-mcp.mcpClientTool",
"position": [
460,
280
],
"parameters": {
"toolName": "={{ $fromAI('tool', 'Set this with the specific tool name') }}",
"operation": "executeTool",
"toolParameters": "={{ /*n8n-auto-generated-fromAI-override*/ $fromAI('Tool_Parameters', ``, 'json') }}"
},
"credentials": {
"mcpClientApi": {
"name": "<your credential>"
}
},
"typeVersion": 1
},
{
"id": "357bde6a-66d0-48dc-972d-d0b35e3868ed",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-120,
280
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "3eba14c5-e4ed-4c4f-8f1d-2b5671b462cc",
"name": "gpt-4o",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-380,
280
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o",
"cachedResultName": "gpt-4o"
},
"options": {}
},
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
},
"typeVersion": 1.2
},
{
"id": "781e5d92-6e9d-4874-93fc-5ea17d11f67f",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
120,
160
],
"parameters": {
"color": 4,
"height": 280,
"content": "## 1\ufe0f\u20e3 MCP Get Brave Tools"
},
"typeVersion": 1
},
{
"id": "78a52697-352f-47ed-a7d2-3a65c9641fd7",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
380,
160
],
"parameters": {
"color": 4,
"height": 280,
"content": "## 2\ufe0f\u20e3 MCP Execute Brave Search"
},
"typeVersion": 1
},
{
"id": "876003d5-7d90-4865-af36-3c0e504b02e7",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-200,
160
],
"parameters": {
"color": 3,
"height": 280,
"content": "## Short Term Chat Memory"
},
"typeVersion": 1
},
{
"id": "9f64f499-73d7-414f-a3d3-02c0417368a6",
"name": "Sticky Note5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-460,
160
],
"parameters": {
"color": 5,
"height": 280,
"content": "## Cloud LLM"
},
"typeVersion": 1
},
{
"id": "fc423452-832c-4377-9bde-04ab6d5c89aa",
"name": "Sticky Note6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-500,
-400
],
"parameters": {
"color": 7,
"width": 1200,
"height": 920,
"content": "# \ud83d\udca5\ud83d\udee0\ufe0fYour First Simple MCP AI Chatbot using Brave Search\nhttps://github.com/nerding-io/n8n-nodes-mcp\nhttps://brave.com/search/api/"
},
"typeVersion": 1
},
{
"id": "5c6c7307-3283-4698-9104-c80df8a62888",
"name": "Sticky Note7",
"type": "n8n-nodes-base.stickyNote",
"position": [
80,
40
],
"parameters": {
"width": 580,
"height": 440,
"content": "## \ud83d\udee0\ufe0f MCP Toolbox\nhttps://github.com/nerding-io/n8n-nodes-mcp\nhttps://brave.com/search/api/"
},
"typeVersion": 1
},
{
"id": "9d1bb515-f8fa-4d48-bbf5-c083f5efd89d",
"name": "Sticky Note8",
"type": "n8n-nodes-base.stickyNote",
"position": [
-360,
-240
],
"parameters": {
"color": 4,
"width": 300,
"height": 240,
"content": "## \ud83d\udc4dTry Me!"
},
"typeVersion": 1
},
{
"id": "b093a455-aee7-4822-b079-7d9cbac783c2",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1060,
-400
],
"parameters": {
"width": 520,
"height": 1040,
"content": "### **Who is this for?**\nThis workflow is ideal for developers, automation enthusiasts, and businesses looking to integrate AI-powered chat capabilities into their workflows. It's particularly useful for those leveraging Brave Search and MCP tools to enhance user interactions and streamline data retrieval.\n\n### **What problem is this workflow solving?**\nThis workflow addresses the challenge of creating an intelligent chatbot that can process user queries, execute searches using Brave Search, and provide responses enriched by AI. It simplifies the integration of multiple tools into a cohesive system, saving time and effort for users who need a robust conversational AI solution.\n\n### **What this workflow does**\n- Listens for incoming chat messages using the **Chat Trigger** node.\n- Processes user input with an **AI Agent** powered by GPT-4o.\n- Retrieves relevant tools using the **MCP Get Brave Tools** node.\n- Executes specific search queries via the **MCP Execute Brave Search** node.\n- Maintains short-term memory of conversations with the **Simple Memory** node.\n\n### **Setup**\n1. **Prerequisites**:\n - Access to an n8n instance (self-hosted).\n - API credentials for OpenAI and MCP Client Tools.\n - Brave Search API key.\n\n2. **Steps**:\n - Import the workflow JSON into your n8n instance.\n - Configure the API credentials for OpenAI and MCP Client Tools in their respective nodes.\n - Set up your Brave Search API key in the MCP nodes. https://brave.com/search/api/\n\n3. **Testing**:\n - Use the built-in chat interface to send test messages.\n - Verify that the chatbot processes queries and returns results as expected.\n\n### **How to customize this workflow to your needs**\n- Modify the AI Agent's prompt settings to tailor responses to your specific use case.\n- Adjust the memory buffer in the Simple Memory node to retain more or less conversational context.\n- Replace or add additional tools in the MCP nodes to expand functionality.\n"
},
"typeVersion": 1
},
{
"id": "8fb4f215-da26-43ad-b187-9b52ed6485ba",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
80,
-280
],
"parameters": {
"width": 580,
"height": 280,
"content": "## \ud83e\udd16 AI Agent with Tools"
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "a555f325-abd3-44bd-ac48-8b0f6910824e",
"connections": {
"gpt-4o": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"MCP Get Brave Tools": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"MCP Execute Brave Search": {
"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.
mcpClientApiopenAiApi
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
How this works
This workflow empowers you to create a responsive web search chatbot that delivers accurate, up-to-date information directly in your conversations, saving hours of manual browsing and research. It's ideal for content creators, customer support teams, or anyone needing quick insights without leaving their chat interface. The core process begins with a chat trigger capturing your query, then leverages GPT-4o to interpret it intelligently, and integrates MCP Brave Search to fetch real-time web results before generating a tailored response.
Use this when building interactive assistants for knowledge queries, like fact-checking or market research, where fresh data from Brave Search enhances AI accuracy. Avoid it for highly specialised domains requiring proprietary databases, or if you need offline functionality. Common variations include swapping Brave for other MCP tools like Wikipedia for historical facts, or adding email notifications for query summaries.
About this workflow
💥🛠️Build a Web Search Chatbot with GPT-4o and MCP Brave Search. Uses agent, chatTrigger, n8n-nodes-mcp, memoryBufferWindow. Chat trigger; 15 nodes.
Source: https://github.com/Zie619/n8n-workflows — original creator credit. Request a take-down →
Related workflows
Workflows that share integrations, category, or trigger type with this one. All free to copy and import.
This n8n workflow template uses community nodes and is only compatible with the self-hosted version of n8n.
This template obtains all the possible tools from Bright Data MCP, process this through chatbot, then run any tool based on the user's query
Disclaimer: This workflow only works with local installations of n8n because it uses a community MCP node
Disclaimer: This template is for self-hosted n8n instances only.
LAB-H-informatic-wu.ac.th copy copy. Uses chatTrigger, memoryBufferWindow, lmChatOpenAi, n8n-nodes-mcp. Chat trigger; 15 nodes.