# Build your own Qdrant vector store MCP server with OpenAI: n8n workflow

> Started by an event in a connected app, and works across Qdrant. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply...

Source: https://millionrounds.com/workflow/build-your-own-qdrant-vector-store-mcp-server-with-openai (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 your own Qdrant vector store MCP server with OpenAI

Started by an event in a connected app, and works across Qdrant. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 37 steps, 3 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-your-own-qdrant-vector-store-mcp-server-with-openai)

**37 steps** Large: read it before trusting it with anything live

**3** Branches: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 3 Model 11 Logic 16 Service 7

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

- 1 **Insert** Tool Workflow *Model*
- 2 **Search** Tool Workflow *Model*
- 3 **Recommend** Tool Workflow *Model*
- 4 **When Executed by Another Workflow** Execute Workflow trigger *Starts it*
- 5 **Compare** Tool Workflow *Model*
- 6 **Embeddings OpenAI** Embeddings Open Ai *Model*
- 7 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 8 **Embeddings OpenAI1** Embeddings Open Ai *Model*
- 9 **ListCompanies** Tool Workflow *Model*
- 10 **When clicking ‘Test workflow’** Manual trigger *Starts it*
- 11 **Qdrant MCP Server** Mcp trigger *Starts it*
- 12 **Operation** Switch *Logic*
- 13 **Insert Reviews** Vector Store Qdrant *Model*
- 14 **Default Data Loader** Document Default Data Loader *Model*
- 15 **Search Reviews** Vector Store Qdrant *Model*
- 16 **Create Collection** Http Request *Service*
- 17 **List by Facet API** Http Request *Service*
- 18 **Get Embeddings1** Http Request *Service*
- 19 **Preferences to Items** Code *Logic*
- 20 **Get Insert Response** Set *Logic*
- 21 **Get Search Response** Aggregate *Logic*
- 22 **Create Facet Index** Http Request *Service*
- 23 **Aggregate Embeddings1** Aggregate *Logic*
- 24 **Get Embeddings** Http Request *Service*
- 25 **Group Search API** Http Request *Service*
- 26 **Aggregate Embeddings** Aggregate *Logic*
- 27 **Split Out Companies** Split Out *Logic*
- 28 **Recommend API** Http Request *Service*
- 29 **Simplify Group Results** Set *Logic*
- 30 **Simplify Recommend Response** Set *Logic*
- 31 **Filter By CompanyId** Filter *Logic*
- 32 **Has Results?1** If *Logic*
- 33 **Has Results?** If *Logic*
- 34 **Aggregate Recommend Response** Aggregate *Logic*
- 35 **Empty Compare Response1** Set *Logic*
- 36 **Aggregate Compare Response** Aggregate *Logic*
- 37 **Empty Compare Response** Set *Logic*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 37, with 3 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Qdrant
- **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 Qdrant 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 37 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 37 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-your-own-qdrant-vector-store-mcp-server-with-openai)
- **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 an MCP server which answers questions with Qdrant** 6 steps · Qdrant](https://millionrounds.com/workflow/build-an-mcp-server-which-answers-questions-with-qdrant)