This workflow corresponds to n8n.io template #3641 — we link there as the canonical source.
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": "L83OjjR3vfmZ0eIc",
"meta": {
"templateCredsSetupCompleted": true
},
"name": "MCP Supabase",
"tags": [],
"nodes": [
{
"id": "3991bb96-f1ee-461a-b515-db32142558c6",
"name": "Create Row",
"type": "n8n-nodes-base.supabaseTool",
"position": [
-360,
-600
],
"parameters": {},
"typeVersion": 1
},
{
"id": "bf55f6bc-4c5f-4869-ab5e-f1af93cb6aa8",
"name": "Delete Row",
"type": "n8n-nodes-base.supabaseTool",
"position": [
-260,
-600
],
"parameters": {},
"typeVersion": 1
},
{
"id": "27e5cf9c-b566-4792-9143-d9b6eda09100",
"name": "Search Single Line",
"type": "n8n-nodes-base.supabaseTool",
"position": [
-20,
-600
],
"parameters": {},
"typeVersion": 1
},
{
"id": "556637e4-079a-4d1c-bb4b-29fbbe1c3224",
"name": "Search All Lines",
"type": "n8n-nodes-base.supabaseTool",
"position": [
120,
-600
],
"parameters": {},
"typeVersion": 1
},
{
"id": "e483de63-b3f4-4702-b364-75b7fe5cfb52",
"name": "Update Line",
"type": "n8n-nodes-base.supabaseTool",
"position": [
-160,
-600
],
"parameters": {},
"typeVersion": 1
},
{
"id": "141d4d1d-4603-4a9a-b6cf-76e2df1107b3",
"name": "MCP Server Supabase",
"type": "@n8n/n8n-nodes-langchain.mcpTrigger",
"position": [
-260,
-760
],
"parameters": {},
"typeVersion": 1
},
{
"id": "33526dbd-e593-43b8-8683-7fffd41cab74",
"name": "AI Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-780,
-760
],
"parameters": {},
"typeVersion": 1.8
},
{
"id": "646d19ca-13b5-4555-b20e-65ec29515c30",
"name": "When chat message received",
"type": "@n8n/n8n-nodes-langchain.chatTrigger",
"position": [
-960,
-740
],
"parameters": {},
"typeVersion": 1.1
},
{
"id": "2e169de1-8f11-4bc7-a0d9-30c79519d2ef",
"name": "Model Chat",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-820,
-600
],
"parameters": {},
"typeVersion": 1.2
},
{
"id": "018376ce-9597-498f-8b3d-3b731efbd7f8",
"name": "Simple Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-700,
-600
],
"parameters": {},
"typeVersion": 1.3
},
{
"id": "1ed67f63-197d-4178-8b6c-5fd26d3a01b5",
"name": "MCP Supabase",
"type": "@n8n/n8n-nodes-langchain.mcpClientTool",
"position": [
-580,
-600
],
"parameters": {},
"typeVersion": 1
},
{
"id": "8b2e910b-4f82-46f2-a354-7cf908d8d89f",
"name": "Sticky Note",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1020,
-1260
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "c27e14ce-100b-41e0-9095-d03bb53c6ebb",
"name": "Sticky Note1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1020,
-880
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "6c8763d4-51ed-432b-972d-62d3e5b2f403",
"name": "Sticky Note2",
"type": "n8n-nodes-base.stickyNote",
"position": [
-400,
-880
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "9f9978f0-e0eb-4a3a-a739-81b3a924cbd7",
"name": "Sticky Note3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-400,
-1260
],
"parameters": {
"content": ""
},
"typeVersion": 1
},
{
"id": "dd2ec159-cda6-4268-8f15-0dd3e262de48",
"name": "Sticky Note4",
"type": "n8n-nodes-base.stickyNote",
"position": [
-1020,
-440
],
"parameters": {
"content": ""
},
"typeVersion": 1
}
],
"active": false,
"settings": {
"executionOrder": "v1"
},
"versionId": "be6f0ca1-6775-4514-918d-9e3225bfb20c",
"connections": {
"Create Row": {
"ai_tool": [
[
{
"node": "MCP Server Supabase",
"type": "ai_tool",
"index": 0
}
]
]
},
"Delete Row": {
"ai_tool": [
[
{
"node": "MCP Server Supabase",
"type": "ai_tool",
"index": 0
}
]
]
},
"Model Chat": {
"ai_languageModel": [
[
{
"node": "AI Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Update Line": {
"ai_tool": [
[
{
"node": "MCP Server Supabase",
"type": "ai_tool",
"index": 0
}
]
]
},
"MCP Supabase": {
"ai_tool": [
[
{
"node": "AI Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Search All Lines": {
"ai_tool": [
[
{
"node": "MCP Server Supabase",
"type": "ai_tool",
"index": 0
}
]
]
},
"Search Single Line": {
"ai_tool": [
[
{
"node": "MCP Server Supabase",
"type": "ai_tool",
"index": 0
}
]
]
},
"When chat message received": {
"main": [
[
{
"node": "AI Agent",
"type": "main",
"index": 0
}
]
]
}
}
}
For the full experience including quality scoring and batch install features for each workflow upgrade to Pro
About this workflow
This workflow was built with love to help you manage your Supabase database using natural language, powered by the MCP (Multi-Channel Protocol) AI Agent on n8n.
Source: https://n8n.io/workflows/3641/ — 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.
Splitout Redis. Uses executeWorkflowTrigger, n8n, redis, splitOut. Event-driven trigger; 46 nodes.
3770. Uses executeWorkflowTrigger, n8n, redis, agent. Event-driven trigger; 46 nodes.
Designing agent tools for outcome rather than utility has been a long recommended practice of mine and it applies well when it comes to building MCP servers; In gist, agents to be making the least amo
Workflow 3770. Uses executeWorkflowTrigger, n8n, redis, agent. Event-driven trigger; 46 nodes.
Build your own N8N Workflows MCP Server. Uses executeWorkflowTrigger, n8n, redis, agent. Event-driven trigger; 46 nodes.