Integration
Connect Knack and OpenAI
When New View Record fires in Knack, your agent runs Create message in OpenAI, or New batch in OpenAI to Create Record in Knack. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Knack and OpenAI to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne 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.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)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)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)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)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)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)Knack holds the records your team works from, and OpenAI can read, classify and write text, images and audio. Connecting them lets a new record in a Knack view kick off a moderation check, a summary or an image in OpenAI, and lets results come back into Knack fields. Work in OpenAI, such as new files or batches, can also be logged as Knack records.
Example flows
What Knack and OpenAI can do together
From Knack to OpenAI
When New View Record in Knack
then Create message in OpenAI
From OpenAI to Knack
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 Knack and OpenAI
Triggers and actions 6 triggers · 80 actions
- New View Record
Fires when a new record appears in a Knack page view — polls a view's records (respects the view's access control and filters), the view-based counterpart to New Record.
- Create Record
Add a new record to a Knack object. Provide field values as a JSON object keyed by field key (e.g. field_1).
- Create View Record
create a record through a view, including inserting a connected record (view-based)
- Delete Record
Delete a record from a Knack object by ID.
- Delete View Record
delete a record through a view (view-based)
- Get Record
Retrieve a single record by ID from a Knack object.
- Get View Record
Retrieve a single record through a page view by its ID — returns only the fields exposed by the view and respects the view's access control, the view-based counterpart to Get Record.
- List Records
Retrieve records from a Knack object, with optional paging and filters.
- List View Records
retrieve records through a view (view-based, applies view permissions/filters)
- Update Record
Update an existing record in a Knack object by ID.
- Update View Record
update a record through a view (view-based)
- Upload File or Image
upload a file or image asset to associate with a record field
- New batch
List your organization's batches.
- New file
Returns a list of files.
- New model
Lists the currently available models.
- New vector store
Returns a list of vector stores.
- New video
List recently generated videos for the current project.
- Cancel batch
Cancels an in-progress batch.
- Cancel run
Cancels a run that is in_progress.
- Cancel vector store file batch
Cancel a vector store file batch.
- Content moderation
Classifies text for hate, harassment, self-harm, sexual, and violence categories using the Moderations API.
- Count input tokens
Returns input token counts of the request.
- Create assistant
Create an assistant with a model and instructions.
- Create chat completion
Sends a list of chat messages to a model via the Chat Completions API and returns the assistant's reply.
- Create completion
Creates a completion for the provided prompt and parameters.
- Create embedding
Generates a vector embedding for input text using an embeddings model (e.g. text-embedding-3-small).
- Create message
Create a message.
- Create run
Create a run.
- Creates and executes a batch from an uploaded file of requests
Creates and executes a batch from an uploaded file of requests
- Create thread
Create a thread.
- Create thread and run
Create a thread and run it in one request.
- Create vector store
Create a vector store.
- Create vector store file
Create a vector store file by attaching a File to a vector store.
- Create vector store file batch
Create a vector store file batch.
- Create video edit job
Create a new video generation job by editing a source or existing generated video.
- Create video extension
Create an extension of a completed video.
- Create video generation job
Create a new video generation job from a prompt and optional reference assets.
- Create video remix
Create a remix of a completed video using a refreshed prompt.
- Delete assistant
Delete an assistant.
- Delete eval run
Delete an eval run.
- Delete file
Delete a file and remove it from all vector stores.
- Delete message
Deletes a message.
- Delete thread
Delete a thread.
- Delete vector store
Delete a vector store.
- Delete vector store file
Delete a vector store file (removes from store, file itself not deleted).
- Delete video
Permanently delete a completed or failed video and its stored assets.
- Download video content
Download the generated video bytes or a derived preview asset.
- Edit image
Creates an edited or extended image given one or more source images and a prompt.
- Generate image
Generates an image from a text prompt using gpt-image-1 / DALL-E and returns the image URL or base64 data.
- Generate speech
Converts text into spoken audio using a TTS model and the selected voice. Returns audio bytes.
- Get assistant
Retrieves an assistant.
- Get batch
Retrieves a batch.
- Get file
Returns information about a specific file.
- Get file content
Returns the contents of the specified file.
- Get message
Retrieve a message.
- Get model
Retrieves a model instance.
- Get run
Retrieves a run.
- Get run step
Retrieves a run step.
- Get thread
Retrieves a thread.
- Get vector store
Retrieves a vector store.
- Get vector store file
Retrieves a vector store file.
- Get vector store file batch
Retrieves a vector store file batch.
- Get vector store file content
Retrieve the parsed contents of a vector store file.
- Get video
Fetch the latest metadata for a generated video.
- List conversation items
List all items for a conversation with the given ID.
- List files
Lists files that have been uploaded to your OpenAI account.
- List messages
Returns a list of messages for a given thread.
- List models
Lists the models currently available to your account.
- List runs
Returns a list of runs belonging to a thread.
- List run steps
Returns a list of run steps belonging to a run.
- List vector store file batch files
Returns a list of vector store files in a batch.
- List vector store files
Returns a list of vector store files.
- OpenAI agent message
Runs one AI agent turn on OpenAI and returns the model's reply. The turn is billed to the OpenAI account connected on this step, and the agent can call the account's AI tool automations.
- Retrieve response
Retrieves a previously created model response by its Response ID.
- Search vector store
Search a vector store for relevant chunks based on a query and filter.
- Send model a message
Sends a message to an OpenAI model via the Responses API and emits its response. Returns a Response ID usable as previous_response_id for multi-turn conversations.
- Submit tool outputs to run
Submit tool outputs when a run requires action.
- Transcribe audio
Transcribes audio into the input language.
- Translate audio
Translates audio into English.
- Update assistant
Modifies an assistant.
- Update message
Modifies a message.
- Update run
Modifies a run.
- Update thread
Modifies a thread.
- Update vector store
Modifies a vector store.
- Update vector store file attributes
Update attributes on a vector store file.
- Upload file
Upload a file that can be used across various endpoints.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Knack
Knack to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Knack to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Knack to MailchimpMailchimp marketing automation and email platform.
Knack to StripeStripe is a payment processing platform for online businesses.
Knack to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
Knack to PipedrivePipedrive is a sales CRM and pipeline management tool.
More into OpenAI
ActiveCampaign to OpenAIActiveCampaign is a marketing automation, email marketing, and CRM platform.
Asana to OpenAIAsana is a collaborative information manager for workspace.
JIRA to OpenAIAtlassian JIRA Cloud — issue tracking and project management.
Twilio to OpenAICloud communications platform for sending SMS/MMS messages, making and managing voice calls, and looking up...
Intercom to OpenAIIntercom is a customer communications platform for support, engagement, and marketing.
Questions
Knack and OpenAI, answered
Can a Knack record trigger work in OpenAI and get the answer back?
Yes. A new record in a Knack view can trigger actions such as content moderation, a chat completion, an embedding or a generated image in OpenAI. The result can then be written back with Update Record or Create Record in Knack.
Which Knack records can start a scenario?
The trigger reads records through a page view, so it respects that view's access control and filters. If you only want certain records to reach OpenAI, set up the view filters first and point the trigger at that view.
What can start an automation from Knack?
Any of Knack's 1 trigger in the catalog, including New View Record. Describe the moment in plain language and your agent picks the right one.
What can your agent do in OpenAI when something happens in Knack?
Any of OpenAI's 69 actions, including Content moderation, Create embedding, Generate image and Create assistant. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from OpenAI to Knack?
Yes. When something happens in OpenAI, your agent can act in Knack too. This page covers both directions: OpenAI's triggers and Knack's actions are listed here as well.
Do I have to build a connector for Knack or OpenAI?
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 Knack and OpenAI 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.