MCP Supabase server for AI agent with RAG: n8n workflow

MCP Supabase server for AI agent with RAG

Started by an event in a connected app, and works across Supabase vectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 23 steps: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

The flow

Starts it 1Model 2Service 20

The steps in the order they run, from what starts it.

1Embeddings OpenAIEmbeddings Open AiModel
2DELETE_ROW_INSCRICOES_CURSOSSupabase ToolService
3GET_ROW_AGENT_MESSAGESupabase ToolService
4CREATE_ROW_AGENT_MESSAGESupabase ToolService
5DELETE_ROW_AGENT_MESSAGESupabase ToolService
6UPDATE_ROW_AGENT_MESSAGESupabase ToolService
7GET_MANY_ROW_AGENT_MESSAGESupabase ToolService
8CREATE_ROW_AGENT_TASKSSupabase ToolService
9GET_ROW_AGENT_TASKSSupabase ToolService
10DELETE_ROW_AGENT_TASKSSupabase ToolService
11UPDATE_ROW_AGENT_TASKSSupabase ToolService
12GET_MANY_ROW_AGENT_TASKSSupabase ToolService
13CREATE_ROW_AGENT_STATUSSupabase ToolService
14GET_ROW_AGENT_STATUSSupabase ToolService
15DELETE_ROW_AGENT_STATUSSupabase ToolService
16UPDATE_ROW_AGENT_STATUSSupabase ToolService
17GET_MANY_ROW_AGENT_STATUSSupabase ToolService
18CREATE_ROW_AGENT_KNOWLEDGESupabase ToolService
19GET_ROW_AGENT_KNOWLEDGESupabase ToolService
20UPDATE_ROW_INSCRICOES_AGENT_KNOWLEDGESupabase ToolService
21GET_MANY_ROW_AGENT_KNOWLEDGESupabase ToolService
22RAGVector Store SupabaseModel
23MCP_SUPABASEMcp triggerStarts it

How it's built

Starts on: An event in a connected app
Steps: 23
Size: Large: read it before trusting it with anything live
Connects to: Supabase vectors
Model: OpenAI
Retrieval: Answers are drawn from documents you supply, not from the model alone

Questions

What does it need to run?

An n8n account, plus your own Supabase vectors account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 23 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 23 steps before you point it at anything that matters.