---
title: "Connect PostgreSQL to Qdrant - APIANT.ai"
description: "When \"New or Updated Row\" fires in PostgreSQL, your agent runs \"Add collection\" in Qdrant."
canonical: "https://apiant.ai/connect/postgresql-to-qdrant"
---

# Connect PostgreSQL to Qdrant

When **New or Updated Row** fires in [PostgreSQL](https://apiant.ai/connections/postgresql), your agent runs **Add collection** in [Qdrant](https://apiant.ai/connections/qdrant). Describe the whole flow and it is built, tested on every scenario and kept running.

PostgreSQL **4** triggers PostgreSQL **6** actions Qdrant **15** actions

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

## What do you want PostgreSQL and Qdrant to do together?

Give your AI client this address.

`https://mcp.apiant.ai`

One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.

### Set it up in your client

### Claude Code

Run this in the directory you want to work in.

`claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai`

Start Claude Code there, approve the server, and sign in in the browser page it opens.

[Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code)

### Claude, web and desktop

Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Cursor

Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Zed

Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Codex and the ChatGPT desktop app

Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

### Any other MCP client

Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.

[Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp)

Example flows

## What PostgreSQL can start in Qdrant

- When **New or Updated Row** in PostgreSQL then **Add collection** in Qdrant
- When **New Row** in PostgreSQL then **Add payload index** in Qdrant

Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.

Everything your agent can do with PostgreSQL and Qdrant

## Triggers and actions 4 triggers · 21 actions

- Trigger

**New or Updated Row**

Triggers when a new row is added or modified.

- Trigger

**New or Updated Row (Custom Query)**

Fires for each new or changed row returned by a SELECT statement you write against the connected PostgreSQL database.

- Trigger

**New Row**

Triggers when you add a new row.

- Trigger

**New Table**

Fires when a new table appears in the connected PostgreSQL database.

- Action

**Add Row**

Adds a new row.

- Action

**Delete Row**

Delete the rows in a table whose chosen column equals a value.

- Action

**Find Row**

Finds a row in a table via a lookup column.

- Action

**Find Rows via Custom Query**

Runs a SELECT statement you write against the connected PostgreSQL database and returns every row it matches.

- Action

**Find Row via Custom Query**

Runs a SELECT statement you write against the connected PostgreSQL database and returns the first row it matches.

- Action

**Update Row**

Updates an existing row.

- Action

**Add collection**

Creates a new Qdrant collection with the given name and vector configuration.

- Action

**Add payload index**

Creates a payload index on a field of a Qdrant collection so that filters on that field run fast.

- Action

**Add points**

Adds points (vectors with optional payloads) to a Qdrant collection, overwriting any existing point with the same id.

- Action

**Add snapshot**

Creates a new snapshot of a Qdrant collection and returns the snapshot's name, size and checksum.

- Action

**Count points**

Returns the number of points in a Qdrant collection, optionally only those matching a payload filter.

- Action

**Delete collection**

Deletes a Qdrant collection and all of the points and data stored in it.

- Action

**Delete points**

Deletes points from a Qdrant collection, either by a list of point ids or by every point matching a filter.

- Action

**Find points by vector**

Returns the points in a collection whose vectors are closest to the vector you supply, ranked by similarity score, with their payloads.

- Action

**Get collection**

Returns the details of a Qdrant collection: its status, point and vector counts, segment count, configuration and payload index schema.

- Action

**Get point**

Returns a single point from a Qdrant collection, including its payload and vector.

- Action

**List collections**

Returns the names of all collections in your Qdrant cluster.

- Action

**List points**

Returns the points stored in a Qdrant collection, optionally narrowed by a payload filter and ordered by a payload field.

- Action

**List snapshots**

Returns every snapshot stored for a Qdrant collection, with each snapshot's file name, creation time, size and checksum.

- Action

**Update collection**

Updates the settings of an existing Qdrant collection, such as its vector, index, optimizer, quantization, strict-mode or metadata parameters.

- Action

**Update point payload**

Sets payload values on points in a Qdrant collection, chosen by point ids or a filter. Keys you supply are added or overwritten; other existing payload keys are kept.

## Each app on its own

- [ **PostgreSQL** Connect directly to a PostgreSQL database and run SQL statements from your automations.](https://apiant.ai/connections/postgresql)
- [ **Qdrant** Vector database and search engine for similarity search, RAG, recommendations, and AI agent retrieval at...](https://apiant.ai/connections/qdrant)

Reviews

## What our customers say

## More from PostgreSQL

- [ **PostgreSQL to GoHighLevel** All-in-one sales and marketing platform agencies white-label and resell to their clients — contacts...](https://apiant.ai/connect/postgresql-to-gohighlevel)
- [ **PostgreSQL to Base64 Encoder/Decoder** Easily convert any file type to a Base64 encoded string and vice versa using our free online converter.](https://apiant.ai/connect/postgresql-to-base64-encoder-decoder)
- [ **PostgreSQL to Echoes** Quotes From Around The World](https://apiant.ai/connect/postgresql-to-echoes)
- [ **PostgreSQL to French Address Search** French Address Search is the French Government's official address geocoding service, built on the Base...](https://apiant.ai/connect/postgresql-to-french-address-search)
- [ **PostgreSQL to NiftyImages** NiftyImages is an email marketing tool that lets you personalize and change images so each recipient sees...](https://apiant.ai/connect/postgresql-to-niftyimages)
- [ **PostgreSQL to PDF Generator API** # Introduction PDF Generator API allows you easily generate transactional PDF documents and reduce the...](https://apiant.ai/connect/postgresql-to-pdf-generator-api)

## More into Qdrant

- [ **HubSpot to Qdrant** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-qdrant)
- [ **Salesforce to Qdrant** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-qdrant)
- [ **Slack to Qdrant** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-qdrant)
- [ **Google Sheets to Qdrant** Google Sheets](https://apiant.ai/connect/google-sheets-to-qdrant)
- [ **Gmail to Qdrant** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-qdrant)
- [ **Google Calendar to Qdrant** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-qdrant)

Questions

## PostgreSQL and Qdrant, answered

###

### What can start an automation from PostgreSQL?

Any of PostgreSQL's 4 triggers in the catalog, including New or Updated Row, New or Updated Row (Custom Query), New Row and New Table. Describe the moment in plain language and your agent picks the right one.

###

### What can your agent do in Qdrant when something happens in PostgreSQL?

Any of Qdrant's 15 actions, including Update collection, Update point payload, Add collection and Add payload index. Your agent maps the data both ways and tests every scenario before it ships.

###

### Can it also run from Qdrant to PostgreSQL?

Qdrant has no triggers in the catalog today, so automations start in PostgreSQL. If you need the other direction, ask: your agent reads Qdrant's API documentation and adds it.

###

### Do I have to build a connector for PostgreSQL or Qdrant?

No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.

###

### Can my AI client use PostgreSQL and Qdrant without building an automation?

Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.

###

### What happens when something fails?

Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.

###

### Is there a free plan?

Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.
