Can NoClick add and delete records in a Chroma collection?

Yes. The Chroma node adds records with their embeddings, reads them back, counts them, and deletes records or entire collections. Wire these to any trigger so new data flows in and stale data is removed without manual steps.

How do I connect Chroma to NoClick?

Add the Chroma node and open its credentials tab to enter your Chroma connection details. Once connected, every operation, from creating a database to forking a collection, runs against your instance.

Can a workflow react to changes in Chroma?

The node is request and response, so it does not fire on its own when Chroma changes. You drive it from other triggers, a schedule, a form submission, or an inbound event, then have it create collections, add records, or read counts as part of the run.

Can it manage collections and databases, not just records?

Yes. Beyond records, the node creates databases, tenants, and collections, counts and deletes collections, forks a collection, and looks one up by ID or CRN. That lets a workflow stand up and tear down vector stores as your projects come and go.

What are the function operations for?

Chroma lets you attach embedding functions to a collection, and the node exposes that. It can attach and detach a function, add a function input, and read which function is currently attached, so records get embedded the way you intend.

How does Codex get access to my apps?

You connect an integration to the agent's tools handle and select which operations to expose. Codex then calls those operations as tools, authenticated with the credentials you connect in NoClick.

Is this the same Codex CLI?

Yes. NoClick runs the Codex harness for you and adds your connected apps as tools. You do not have to install or manage anything locally.

Can I trigger a Codex agent automatically?

Yes. Because it runs hosted, you can start it from a schedule, a webhook, or another app event, not just by hand.

Which apps can I connect?

Any of NoClick’s tool-provider integrations, from Slack and Linear to GitHub, Notion, Google Sheets, Postgres, and dozens more.

Codex

Connect Codex to Chroma

Give an AI agent your Chroma instance as a tool and it can manage the vector store itself instead of asking you to. It can create a collection, add records, read and count what is stored, fork a collection for a safe experiment, and delete records that no longer belong, calling each operation as a tool while it works a task. Wire it into a hosted coding agent in NoClick and it can build and maintain a retrieval index end to end.

Loading preview…

Opens a workflow with 36 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 Codex, or hosted in the cloud. The rest of setup adapts to your choice:
Pick what it can do in Chroma
A preset of real Chroma operations. Each one becomes a tool the agent can call, and it can't touch anything outside the list.
Connect Chroma
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 Codex first calls in.
Run this in your terminal
$codex mcp add noclick --url https://mcp.noclick.app/s/<your-link>
<your-link> is your personal server URL — setup mints it for you.

Exact capabilities

Tools Codex gets

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

Chroma

36 tools

Query (Vector)

Similarity search by a query embedding vector.

Search (Text)

Full-text / semantic search using query text — Chroma embeds it server-side via an attached function.

Add Records

Add records to a collection (fails if IDs already exist; use Upsert for insert-or-update).

Upsert Records

Upsert records — inserts new IDs and updates existing ones (idempotent sync).

Update Records

Update existing records by ID (fails if an ID does not exist; use Upsert otherwise).

Get Records

Get records by ID or filter.

Count Records

Count the number of records in a collection.

Delete Records

Delete records by ID, metadata filter, or document content filter.

Upload & Index Document

Upload a document file, chunk + embed it, and add the records.

List Collections

List collections in the tenant/database.

Get Collection

Get a collection's metadata and configuration by name.

Create Collection

Create a collection.

Update Collection

Rename a collection or replace its metadata.

Delete Collection

Permanently delete a collection and all its records.

Count Collections

Count the total number of collections in the database.

Indexing Status

Get the indexing status of a collection (records indexed vs pending).

Fork Collection

Fork (copy) an existing collection into a new one.

Fork Count

Get the number of times a collection has been forked.

Get Collection by ID

Get a collection's metadata by its UUID.

Get Collection by CRN

Get a collection by its Cloud Resource Name (CRN).

Attach Function

Attach an embedding or processing function to a collection.

Get Attached Function

Get details about a function attached to a collection.

Add Function Input

Add input data to an attached function (e.g. provide documents to embed).

Detach Function

Detach (remove) a function from a collection.

Get Tenant

Get metadata about a tenant.

Create Tenant

Create a new tenant.

Update Tenant

Update a tenant's configuration.

List Databases

List all databases in the tenant.

Create Database

Create a new database in the tenant.

Get Database

Get metadata about a database.

Delete Database

Delete a database and ALL its collections. DESTRUCTIVE.

Healthcheck

Check whether the Chroma server is healthy.

Heartbeat

Get the server heartbeat (nanosecond timestamp).

Get Version

Get the Chroma server version string.

Reset Server

Reset the Chroma server. DESTRUCTIVE — wipes ALL data across all tenants and databases.

Get User Identity

Get the identity of the currently authenticated user.

Starting points

What you can build

When a new document lands in your pipeline, embed it and add the records to the right Chroma collection automatically.

On a schedule, count the records in each collection and post the totals to your team so you can watch the index grow.

When a source record is deleted upstream, delete the matching records from Chroma so search never returns stale hits.

Stand up a fresh database and collection for each new project, then attach an embedding function so records are ready to store.

Fork a production collection before a risky reindex, run the changes against the copy, and leave the original untouched.

Look up a collection by ID or CRN, pull its records, and feed them into an AI step for evaluation or cleanup.

Meet the runner

About Codex

Codex is OpenAI's command-line coding agent. NoClick runs it as a hosted agent and lets you connect your apps to it as tools, turning it from a coding assistant into an operator that can act across your systems. Connect an integration to the agent and Codex can query, create, and update records in that app directly. You keep the Codex experience and give it real reach into the tools your team already uses.

Fast, capable code generation and editing

Good at well-scoped, concrete tasks

Strong at API and data manipulation

Familiar to teams already on OpenAI tooling

Good to know