Can NoClick add and update vectors in Qdrant automatically?

Yes. The node upserts points, uploads and indexes documents, and updates collection settings, so any trigger can push fresh embeddings into Qdrant. You can also delete points or clear payloads to keep a collection current as records change.

How do I connect the Qdrant node?

It authenticates with an API key and your cluster URL, whether that is Qdrant Cloud or a self-hosted server. Once the credential is saved, every operation in the workflow reuses the same connection, so you set it up once.

Can a workflow run a semantic search over my collection?

Yes. Use Query / Search to find the nearest vectors to a given embedding, or Recommend Points to surface items similar to a set of examples. Retrieve Points and Scroll Points let you pull specific records by ID or page through the whole collection.

Can it manage payload metadata, not just the vectors?

It can. Set Payload writes metadata onto points, while Clear Payload and Delete Payload Keys remove it, and Create Payload Index and Delete Payload Index control which fields are indexed for filtering. That lets one workflow keep both the vectors and their attached metadata in order.

Can a workflow react to changes in Qdrant?

The Qdrant node is request and response, so it does not fire on its own. You trigger it from another node, a schedule, a form, or an inbound webhook, then use List Collections, Count Points, or Get Collection Info to check the state of a collection as part of that run.

Hermes is an open agent based on Nous Research’s Hermes models. NoClick runs it for you and adds your connected apps as tools.

How do I give Hermes access to an app?

Connect the app's integration node to the agent's tools handle and pick the operations to expose. Each becomes a callable tool.

Do I need my own infrastructure?

No. The harness runs in a hosted sandbox and NoClick handles credentials for the apps you connect.

Can Hermes use multiple apps at once?

Yes. Wire in several integrations and the agent can use them together in a single run.

Connect Hermes to Qdrant

Give an AI agent your Qdrant instance as a tool and it can manage its own search index and long-term memory while it works. It can create a collection, upsert points, run a vector query or a recommendation, retrieve or scroll matching records, and set or clear payload metadata on its own, calling each operation as a tool. That turns retrieval from a fixed pipeline into something the agent drives directly, storing what it learns and searching it back when it needs context.

Loading preview…

Opens a workflow with 18 tools ready to use.

What happens next

Set up in minutes

The open button drops you into a guided setup. It asks exactly this, nothing else:

Choose where it runs
On your computer through your own Hermes, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Qdrant
A preset of real Qdrant operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Qdrant
One sign-in. The agent acts through your account, scoped to the operations you picked.
Add your personal MCP link
The last step mints a private MCP URL for this agent and walks you through exactly this, with your real link filled in. The page flips to Connected the moment your Hermes first calls in.
1. Run this in your terminal
$hermes mcp add noclick --url https://mcp.noclick.app/s/<your-link>
2. Answer no when asked if the server requires authentication — the link itself is the key
<your-link> is your personal server URL — setup mints it for you.

Exact capabilities

Tools Hermes gets

Pick the operations you want and each becomes a tool the agent can call directly while it works.

Qdrant

18 tools

Query / Search

Find the most similar points to a query vector (similarity search).

Upsert Points

Insert or overwrite points in a collection.

Retrieve Points

Retrieve points by their IDs.

Delete Points

Delete points by ID or by filter.

Scroll Points

Scroll through all points in a collection with optional filter and cursor-based pagination.

Count Points

Count points in a collection, with optional filter.

Recommend Points

Find points similar to positive examples and dissimilar from negative examples.

List Collections

List all collections.

Get Collection Info

Get detailed info and stats for a single collection.

Create Collection

Create a new collection.

Update Collection

Update collection parameters (optimizers, HNSW, quantization).

Delete Collection

Delete a collection and all its points permanently.

Set Payload

Set (merge) payload fields on points selected by IDs or filter.

Delete Payload Keys

Delete specific payload keys from points.

Clear Payload

Remove all payload from points selected by IDs or filter.

Create Payload Index

Create a payload field index to speed up filtered searches.

Delete Payload Index

Delete a payload field index.

Upload & Index Document

Upload a document file, chunk + embed it, and upsert the points.

Starting points

What you can build

When a new document lands in your pipeline, embed it and call Upload and Index Document to add it to a Qdrant collection automatically.

On each incoming support ticket, run a Query / Search against your knowledge base collection and return the closest matching articles.

Every night, use Scroll Points to page through a collection and Delete Points for records that are past their retention window.

When a product is updated, upsert its new embedding with Upsert Points and refresh its metadata with Set Payload in the same run.

Feed a customer's recent purchases into Recommend Points to surface similar items for a personalized follow-up email.

Before a bulk import, call Create Collection with the right vector size and add a Create Payload Index so filtered searches stay fast.

Meet the runner

About Hermes

Hermes is an open agent built on Nous Research’s Hermes models. NoClick runs it hosted and connects your apps to it as tools, so it can do real work across your systems. Wire an integration into the agent and Hermes can use that app’s operations directly while it reasons through a task. It is a strong pick when you want an open-model agent with genuine tool access.

Built on open Hermes models

Capable general reasoning

Flexible, open-model foundation

Hosted with apps wired in as tools

Good to know