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 →
{
"name": "puppeteer-agent",
"nodes": [
{
"parameters": {
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"typeVersion": 1.1,
"position": [
680,
-180
],
"id": "d05be2a2-0322-4e29-8f11-6f2081d44893",
"name": "When chat message received"
},
{
"parameters": {
"promptType": "define",
"text": "={{ $json.input }}",
"options": {
"systemMessage": "You are an AI agent with browser automation capabilities through Puppeteer. You can help users navigate websites, capture screenshots, interact with web elements, and execute JavaScript in a real browser environment.\n\n## Your Capabilities and Available Tools\n\nYou have access to the following Puppeteer tools:\n\n1. **puppeteer_navigate** - Navigate to any URL in the browser\n - Required input: `url` (string)\n - Optional inputs: `launchOptions` (object), `allowDangerous` (boolean)\n\n2. **puppeteer_screenshot** - Capture images of full pages or specific elements\n - Required input: `name` (string)\n - Optional inputs: `selector` (string), `width` (number), `height` (number), `encoded` (boolean)\n\n3. **puppeteer_click** - Click on elements using CSS selectors\n - Required input: `selector` (string)\n\n4. **puppeteer_hover** - Hover over elements using CSS selectors\n - Required input: `selector` (string)\n\n5. **puppeteer_fill** - Enter text into input fields\n - Required inputs: `selector` (string), `value` (string)\n\n6. **puppeteer_select** - Choose options from dropdown menus\n - Required inputs: `selector` (string), `value` (string)\n\n7. **puppeteer_evaluate** - Execute custom JavaScript in the browser context\n - Required input: `script` (string)\n\nYou can also access these resources:\n- Console logs via `console://logs`\n- Screenshots via `screenshot://<name>`\n\n## How to Use Your Tools\n\nWhen a user requests web automation, follow these steps:\n\n1. **Understand the request** - Ask clarifying questions if needed to determine which websites to visit and what actions to perform\n2. **Plan your approach** - Break down complex tasks into individual steps\n3. **Execute tools sequentially** - Run tools in a logical order to accomplish the task\n4. **Provide updates** - Inform the user of your progress after each significant action\n5. **Show results** - Share screenshots and relevant information from the browser\n\n## Tool Usage Guidelines\n\n- **Always use puppeteer_navigate** before attempting other actions\n- **Be specific with CSS selectors** when targeting elements with puppeteer_click, puppeteer_hover, puppeteer_fill, and puppeteer_select\n- **Respect loading times** between actions when interacting with web pages\n- **Use puppeteer_screenshot** to show progress and results\n- **Use puppeteer_evaluate** cautiously and only when necessary\n- **Report any errors** encountered during automation\n\n## Privacy & Security Considerations\n\n- **Do not** store or transmit sensitive user data\n- **Do not** accept or execute custom launch options unless explicitly trusted\n- **Never set allowDangerous to true** in puppeteer_navigate unless absolutely necessary and user-verified\n\nWhen using your tools, always be transparent about what you're doing and why. If you encounter a request that seems potentially harmful or unethical, politely decline and suggest alternatives."
}
},
"type": "@n8n/n8n-nodes-langchain.agent",
"typeVersion": 1.9,
"position": [
612,
0
],
"id": "57e97b6b-829c-446b-b21d-dfdbe7b34ea5",
"name": "AI Agent"
},
{
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"typeVersion": 1.2,
"position": [
220,
220
],
"id": "126865b8-05ad-46c3-926e-e044d8b8c470",
"name": "OpenAI Chat Model",
"credentials": {
"openAiApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"connectionType": "sse"
},
"type": "n8n-nodes-mcp.mcpClientTool",
"typeVersion": 1,
"position": [
340,
220
],
"id": "a0844e99-7330-465b-8468-12a2c7ba16a7",
"name": "MCP Client",
"credentials": {
"mcpClientSseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"connectionType": "sse",
"operation": "executeTool",
"toolName": "puppeteer_navigate"
},
"type": "n8n-nodes-mcp.mcpClientTool",
"typeVersion": 1,
"position": [
460,
220
],
"id": "01bf4b51-48ea-45fe-94d6-282e65b7a5c4",
"name": "puppeteer_navigate",
"credentials": {
"mcpClientSseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"connectionType": "sse",
"operation": "executeTool",
"toolName": "puppeteer_screenshot"
},
"type": "n8n-nodes-mcp.mcpClientTool",
"typeVersion": 1,
"position": [
580,
220
],
"id": "c7470227-1036-4632-b492-ea339f0e8574",
"name": "puppeteer_screenshot",
"credentials": {
"mcpClientSseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"connectionType": "sse",
"operation": "executeTool",
"toolName": "puppeteer_click"
},
"type": "n8n-nodes-mcp.mcpClientTool",
"typeVersion": 1,
"position": [
700,
220
],
"id": "a0c4d1a9-214c-4873-bf49-3c2bd2818539",
"name": "puppeteer_click",
"credentials": {
"mcpClientSseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"connectionType": "sse",
"operation": "executeTool",
"toolName": "puppeteer_fill"
},
"type": "n8n-nodes-mcp.mcpClientTool",
"typeVersion": 1,
"position": [
820,
220
],
"id": "bb58057c-6b15-4372-bc54-b8e5dbc5a8f1",
"name": "puppeteer_fill",
"credentials": {
"mcpClientSseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"connectionType": "sse",
"operation": "executeTool",
"toolName": "puppeteer_select"
},
"type": "n8n-nodes-mcp.mcpClientTool",
"typeVersion": 1,
"position": [
940,
220
],
"id": "3faff4fc-d0d8-46b3-be1f-0a0acd958790",
"name": "puppeteer_select",
"credentials": {
"mcpClientSseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"connectionType": "sse",
"operation": "executeTool",
"toolName": "puppeteer_hover"
},
"type": "n8n-nodes-mcp.mcpClientTool",
"typeVersion": 1,
"position": [
1060,
220
],
"id": "b603ca36-7896-42d6-8117-309c5475b365",
"name": "puppeteer_hover",
"credentials": {
"mcpClientSseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"connectionType": "sse",
"operation": "executeTool",
"toolName": "puppeteer_evaluate"
},
"type": "n8n-nodes-mcp.mcpClientTool",
"typeVersion": 1,
"position": [
1180,
220
],
"id": "39221c40-7066-4bc7-bfaa-9622dfda5448",
"name": "puppeteer_evaluate",
"credentials": {
"mcpClientSseApi": {
"name": "<your credential>"
}
}
},
{
"parameters": {
"inputSource": "jsonExample",
"jsonExample": "{\n \"input\": \"take a screenshot of our company website\",\n \"reason\": \"The request involves web automation to capture a screenshot, which is a primary capability of the Puppeteer Agent.\",\n \"selectedAgent\": \"puppeteer-agent\"\n}"
},
"type": "n8n-nodes-base.executeWorkflowTrigger",
"typeVersion": 1.1,
"position": [
340,
0
],
"id": "5a0c3061-c9cd-469a-915a-e4683d4f5b42",
"name": "When Executed by Another Workflow"
}
],
"connections": {
"When chat message received": {
"main": [
[]
]
},
"OpenAI Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"MCP Client": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"puppeteer_navigate": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"puppeteer_screenshot": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"puppeteer_click": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"puppeteer_fill": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"puppeteer_select": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"puppeteer_hover": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"puppeteer_evaluate": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"When Executed by Another Workflow": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
}
},
"active": true,
"settings": {
"executionOrder": "v1"
},
"versionId": "49b231db-1390-423b-a8be-15bda13c8030",
"meta": {
"templateCredsSetupCompleted": true
},
"id": "ac0gXz0B2sAQMmVd",
"tags": []
}
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.
openAiApi
Pro
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
puppeteer-agent. Uses chatTrigger, lmChatOpenAi, executeWorkflowTrigger, agent. Chat trigger; 5 nodes.
Source: https://github.com/dujonwalker/project-nova/blob/1cfff76201b1f929687d3d0b2e93aa82f4633418/n8n-workflows/puppeteer_agent.json — 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.
flowise-agent. Uses chatTrigger, lmChatOpenAi, executeWorkflowTrigger, agent. Chat trigger; 5 nodes.
Chat Trigger, OpenAI Chat, Execute Workflow Trigger +2
ragflow-agent. Uses chatTrigger, lmChatOpenAi, executeWorkflowTrigger, agent. Chat trigger; 5 nodes.
Chat Trigger, OpenAI Chat, Execute Workflow Trigger +2
memos-agent. Uses chatTrigger, lmChatOpenAi, executeWorkflowTrigger, agent. Chat trigger; 5 nodes.
Chat Trigger, OpenAI Chat, Execute Workflow Trigger +2
karakeep-agent. Uses chatTrigger, lmChatOpenAi, executeWorkflowTrigger, agent. Chat trigger; 5 nodes.
Chat Trigger, OpenAI Chat, Execute Workflow Trigger +2
fetch-agent. Uses chatTrigger, lmChatOpenAi, mcpClientTool, executeWorkflowTrigger. Chat trigger; 5 nodes.
Chat Trigger, OpenAI Chat, Mcp Client Tool +2