Automation library · Setup and learning

Build an MCP server which answers questions with Qdrant

Started by someone submitting a form, and works across Qdrant. 6 steps: small enough to read in one sitting and change without fear.

SmallRetrieval

6 stepsSmall: readable in one sitting
0Branches: places the flow splits
0Loops or waits
1Service it connects to

The flow

Starts it 2Model 4

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

  1. 1Embeddings OllamaEmbeddings OllamaModel
  2. 2On form submissionForm triggerStarts it
  3. 3Default Data LoaderDocument Default Data LoaderModel
  4. 4Qdrant Vector StoreVector Store QdrantModel
  5. 5Qdrant Vector Store1Vector Store QdrantModel
  6. 6MCP Server TriggerMcp triggerStarts it

How it's built

Starts on
Someone submitting a form
Steps
6
Size
Small: readable in one sitting
Connects to
Qdrant
Model
None. This is plumbing, not judgement
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 Qdrant account. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone submitting a form.

Does it use AI?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Not long. At 6 steps it can be read in one sitting and changed without fear.

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 6 steps before you point it at anything that matters.