# Build an MCP server which answers questions with Qdrant: n8n workflow

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

Source: https://millionrounds.com/workflow/build-an-mcp-server-which-answers-questions-with-qdrant (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Setup and learning](https://millionrounds.com/workflows?category=Setup+and+learning#library)

# 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.

Small Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-an-mcp-server-which-answers-questions-with-qdrant)

**6 steps** Small: readable in one sitting

**0** Branches: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 2 Model 4

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

- 1 **Embeddings Ollama** Embeddings Ollama *Model*
- 2 **On form submission** Form trigger *Starts it*
- 3 **Default Data Loader** Document Default Data Loader *Model*
- 4 **Qdrant Vector Store** Vector Store Qdrant *Model*
- 5 **Qdrant Vector Store1** Vector Store Qdrant *Model*
- 6 **MCP Server Trigger** Mcp trigger *Starts 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.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-an-mcp-server-which-answers-questions-with-qdrant)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[Qdrant](https://millionrounds.com/workflows?service=Qdrant#library)

## Workflows like it

Also setup and learning, with the same services where possible, closest in size first.

- [**Build your own Qdrant vector store MCP server with OpenAI** 37 steps · calls a model · Qdrant](https://millionrounds.com/workflow/build-your-own-qdrant-vector-store-mcp-server-with-openai)