Skip to content
Qdrant logo

Connectors / Data and analytics · HTTP Connector

Automate Qdrant with Tray.ai

Create a collection, create a snapshot and update collection aliases in Qdrant. Connect Qdrant to the rest of your data and analytics stack with Tray.ai.

What can you do with Qdrant on Tray.ai?

Qdrant is a vector database and search engine that stores embeddings with attached data and finds the closest matches for semantic search and AI retrieval. Tray.ai connects to Qdrant through the HTTP Connector, so your workflows can call the Qdrant API alongside the rest of your stack.

  • Upsert points for each new help article in your knowledge base, so search finds it by meaning.
  • Query points with a customer question from your help desk to suggest related articles.
  • Delete points when a document is removed from your document storage.
Connects through
HTTP Connector
Authentication
An API key in a request header or a bearer token

Set it up

Connect Qdrant to Tray.ai

Each step uses Qdrant's own API details, from its documentation.

Step 1

Save Qdrant's API key

Save the key as a Tray.ai authentication. The HTTP Client puts it in the request header, read from $.auth. The key stays out of the workflow and out of the logs.

Step 2

Import a request from Qdrant's docs

Add an HTTP Client step and paste a cURL example from Qdrant's API docs. Tray.ai fills in the method, URL, headers, and query.

Step 3

Start with “List all collections”

It's one of 18 documented actions, under Collections. The response comes back as data the next step can map into your other apps.

Step 4

Hand it to an AI agent

Wrap “Create a collection” and “Update collection parameters” in workflows, and Tray.ai's Agent Gateway for MCP publishes them as governed tools Claude and other AI agents can call.

Workflows to build with Qdrant

Each one uses actions and events from Qdrant's own API documentation.

Index new Confluence pages in Qdrant for search

When

A page is published in Confluence

Then

  1. Upsert points with the page embedding and link
  2. Count points to confirm the collection size

With Confluence

Index solved Zendesk tickets in Qdrant

When

A ticket is solved in Zendesk

Then

  1. Query points to skip tickets already indexed
  2. Upsert points with the ticket text embedding and tags

With Zendesk

Back up Qdrant collections to Box

When

On a schedule

Then

  1. List all collections
  2. Create a snapshot of each collection
  3. Download a snapshot and save it to Box

With Box

Apps you can build on Qdrant data

Internal tools your team can build with an AI assistant, each one using Qdrant calls from its API documentation.

Collection health view

Lists vector collections with point counts and snapshots so the data team can check index health.

Search test console

Lets engineers run a test query against a collection and inspect the matching points and their payloads.

Snapshot manager

Lists collection snapshots and lets the team take a new backup or remove old ones.

Give your AI agents Qdrant tools

Build an MCP server on Qdrant in Agent Gateway and choose which actions your agents can call. Every call runs with access control and an audit trail. How Agent Gateway works

  • List all collections
  • Upsert points
  • Query points
  • List collection snapshots
  • List all aliases
  • Create a collection
  • Update collection parameters
  • Delete a collection

What the Qdrant API covers

5 resources and 18 documented actions, each one a call the HTTP Connector can make from a Tray.ai workflow. Connecting it takes a few clicks: here's how.

Collections

  • List all collections
  • Create a collection
  • Update collection parameters
  • Delete a collection

Points

  • Upsert points
  • Retrieve points
  • Delete points
  • Set point payload
  • Count points

Search

  • Query points
  • Query points in batch
  • Query point groups

Snapshots

  • List collection snapshots
  • Create a snapshot
  • Download a snapshot
  • Delete a snapshot

Aliases

  • List all aliases
  • Update collection aliases

Checked against Qdrant's own documentation on 2026-10-22

api.qdrant.tech/api-reference

Frequently asked questions

What can a Tray.ai workflow do in Qdrant?

+

The Qdrant API documents 18 actions across 5 resources (Collections, Points, Search, Snapshots, Aliases). For example: List all collections; Upsert points; Query points. A workflow can make any documented call through the HTTP Connector.

How does Tray.ai authenticate with Qdrant?

+

The Qdrant API uses an API key in a request header and a bearer token. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.

See Qdrant working against your stack.

We'll walk through a tailored demo with your systems plugged in.

Great — a couple more details

This helps us connect you with the right person. Optional, and you can skip it.