Integration
Connect Mindstamp and OpenAI
When New Interaction fires in Mindstamp, your agent runs Create message in OpenAI, or New batch in OpenAI to Add videos to a group in Mindstamp. 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 Mindstamp 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)Grok
Open grok.com/connectors, choose New Connector, then Custom, and paste the address. Grok signs you in in your browser.
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)Example flows
What Mindstamp and OpenAI can do together
From Mindstamp to OpenAI
When New Interaction in Mindstamp
then Create message in OpenAI
From OpenAI to Mindstamp
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 Mindstamp and OpenAI
Triggers and actions 8 triggers · 155 actions
- New Interaction
Triggers when a viewer makes a new interaction with one of your videos.
- New Lead
Triggers when a viewer becomes a new lead by submitting their name, email, phone or custom ID in one of your videos.
- New View
Triggers when a new view of one of your videos takes place.
- Add videos to a group
Add videos to a specified group by providing a comma-separated list of video tokens or IDs (e.g., ?videos=aAZdX124,ac8a6df7-5dd1-4e34-97f6-cdb54efc59a5)
- Add videos to a series
Add videos to a specified series by providing a comma-separated list of video tokens or IDs (e.g., ?videos=aAZdX124,ac8a6df7-5dd1-4e34-97f6-cdb54efc59a5)
- Attach a certificate to a video
Attach a certificate design to a video with the rules for this video. The response has the click_action and click_value that give the certificate from a button, a hotspot, or a question answer. Set end_screen to give it on the end screen. A design ca
- Cancel a dub job
Cancel a queued or processing dub job.
- Create a new Access List
Create a new Access List for your organization. Provide a name, description, and entries in the format for email---name---passcode (e.g., ?name=My List,description=My new access list,entries=john.doe@email.com---John---pa$$,jane.doe@email.com---Jane-
- Create a new Access List Entry
Create a new Access List Entry for a specified Access List.
- Create or start a video transcript
Start transcript creation for a video, or return the existing transcript job when one already exists.
- Delete a captions file
Remove captions by ID
- Delete an asset
Remove the asset from the library, the same as delete on the Assets page. Interactions that already use it keep working.
- Delete an interaction
Delete an existing API-created annotation except questions.
- Delete a question
Delete an existing question interaction. Use the id returned by the question create endpoint.
- Delete a Video
Soft-delete an existing video immediately and enqueue background cleanup. The endpoint is idempotent; deleting an already-deleted video returns the same success response.
- Get account design
Return the organization owner account-level design. API tokens always resolve account design through the organization owner.
- Get a certificate
Get a certificate
- Get admin-created annotations for a single video
Returns admin-created annotations such as buttons, questions, images, hotspots, and text. Does not include viewer interactions.
- Get a dub job
Return current job status, language track status, progress, billing details, and errors.
- Get a list of Access Lists
Return details pertaining to the Access Lists of the current user's organization.
- Get a list of groups
Return details pertaining to all groups associated with your account/organization.
- Get a list of Personalized Links
Return details pertaining to the Personalized Links of the current user.
- Get a list of series
Return details pertaining to all series associated with your account/organization.
- Get a list of videos
Return details pertaining to all videos associated with your account/organization.
- Get a list of viewers
Return details pertaining to all viewers associated with your account/organization.
- Get a list of views
Return details pertaining to all views associated with your account/organization.
- Get all interactions
Return details pertaining to all interactions associated with your account/organization.
- Get all views for a single viewer
Return view details pertaining to a specific viewer associated with a viewer ID.
- Get an asset
Get an asset
- Get a new upload ticket
Issue fresh TUS credentials for a video that is still waiting for its file, for example after the first ticket expired during a long transfer. The ticket points at the same upload slot, so a TUS client can resume. Answers 409 once bytes have arrived,
- Get an issued certificate
Get an issued certificate
- Get API status
Return a simple API status message. This endpoint does not require authentication.
- Get a single Access List
Return details pertaining to a specific Access List associated with an Access List ID.
- Get a single Captions object
Get a captions object by ID
- Get a single group
Return details pertaining to a specific group associated with a group ID.
- Get a single interaction
Return details pertaining to a specific interaction associated with an ID.
- Get a single Personalized Link
Return details pertaining to a specific Personalized Link associated with a Personalized Link ID.
- Get a single series
Return details pertaining to a specific series associated with a series ID.
- Get a single video
Return details pertaining to a specific video associated with a video ID.
- Get a single view
Return details pertaining to a specific view associated with a view ID.
- Get a single viewer
Return details pertaining to a specific viewer associated with a viewer ID.
- Get current user
Return the authenticated user and organization name.
- Get insights
Return insights for a specified video, series, group, or tag
- Get insights for a single video
Return insights for a specific video ID or token.
- Get interactions for a single view
Return details pertaining to all interactions associated with a view ID.
- Get interactions for a single viewer
Return interaction details pertaining to a specific viewer associated with a viewer ID.
- Get media status
Media state for a video. For file uploads each call refreshes the state from the media service and stores the duration once the file is ready. Poll this after a TUS upload until state is ready. A URL video reports ready at once.
- Get monthly view summary
Return per-video view counts for the current month.
- Get the branches for a single video
Return videos that this video branches to.
- Get the captions for a video
See all captions currently available for a video
- Get the chapters for a single video
Return details pertaining to all chapters associated with a video ID.
- Get the interactions for a single group
Return details pertaining to all interactions associated with a group ID.
- Get the interactions for a single series
Return details pertaining to all interactions associated with a series ID.
- Get the interactions for a single video
Return details pertaining to all interactions associated with a video ID.
- Get the responses to a single interaction
Return response details pertaining to a specific interaction associated with an ID.
- Get the videos for a single group
Return details pertaining to all videos associated with a group ID.
- Get the videos for a single series
Return details pertaining to all videos associated with a series ID.
- Get the views for a single group
Return details pertaining to all views associated with a group ID.
- Get the views for a single series
Return details pertaining to all views associated with a series ID.
- Get the views for a single video
Return details pertaining to all views associated with a video ID.
- Get video design
Return the design for a video in your organization.
- Get video settings
Return the fields on the Settings page of a video.
- Get video transcript status
Return the transcript for a video, with timed text in chunks and sentences. Mindstamp creates a transcript automatically for each new MP4 or uploaded file on a paid plan. To get the words in a time window, convert the window to milliseconds and selec
- Get video translation state
Return transcript readiness, published translation languages, and recent dub jobs for a video.
- Get view summary
Return aggregate view, interaction, viewer, and watch-time totals.
- Get weekly view summary
Return per-video view counts for the current week.
- Invite users to a group
Add users to a specified group by providing a comma-separated list of emails
- Invite users to a series
Add users to a specified series by providing a comma-separated list of emails
- List assets
List one kind of asset in the shared library, newest first. These are the same files as the Assets page in the editor.
- List certificates
List the certificate designs in the account library, newest first. These are the same designs as the Certificates page in the editor.
- List issued certificates
List the certificates that viewers earned, newest first.
- List supported translation languages
Return the language codes and variants that can be used for interaction translation and full audio dubbing.
- List the certificates on a video
List the certificates on a video
- Personalize a video
Create a personalized link for a video. Additional query parameters are encoded into the personalized key.
- Quote a video translation job
Return estimated price, quota usage, paid minutes, and languages that are already purchased for the video.
- Remove an Access List Entry
Remove an Access List Entry for a specified Access List.
- Remove the certificate from a video
Same as removing it in the editor. Buttons and answers that point to it stop giving it, and an end screen that gives it changes to none. Issued certificates stay valid.
- Retry a dub job
Retry failed language tracks when possible. If no language track is failed, all tracks are queued again. Already purchased languages are not billed again.
- Retry one failed dub language
Retry one failed language track without restarting successful language tracks.
- Update account design
Update the account design of the organization owner.
- Update an asset
Change the title, tags, or file URL. Send only the fields to change.
- Update an interaction
Update an existing API-created annotation.
- Update a Personalized Link's status
Update a Personalized Link from active to inactive and vice versa.
- Update a question
Update an existing question interaction. Use the id returned by the question create endpoint. Legacy API-created question identifiers are also resolved through the annotation record when available.
- Update a Video
Update an existing video
- Update the certificate on a video
Change the rules. Send only the fields to change.
- Update video design
Update the design of one video in your organization. To use your own font, upload the font files in the editor (Design, Font, Add custom font), or host the files yourself and send font_family with custom_font. Font files on another host must allow cr
- Update video settings
Change fields on the Settings page of a video. Send a JSON body with only the fields to change. The response contains all settings. Design fields, such as guide_transcript, use Update video design.
- 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.
- Ask docs with file search
Asks an OpenAI model a question answered from a vector store via the Responses API file_search tool, and returns just the reply text. Authenticates with this account's own OpenAI connection, unlike the platform AI Agent step which requires a platform-level system key.
- 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 Mindstamp
Mindstamp to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Mindstamp to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Mindstamp to StripeStripe is a payment processing platform for online businesses.
Mindstamp to ShopifyShopify is a commerce platform for online stores and retail point-of-sale.
Mindstamp to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
Mindstamp to PipedrivePipedrive is a sales CRM and pipeline management tool.
More into OpenAI
Mailchimp to OpenAIMailchimp marketing automation and email platform.
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
Mindstamp and OpenAI, answered
What can start an automation from Mindstamp?
Any of Mindstamp's 3 triggers in the catalog, including New Interaction, New Lead and New View. Describe the moment in plain language and your agent picks the right one.
What can your agent do in OpenAI when something happens in Mindstamp?
Any of OpenAI's 70 actions, including Create assistant, Create chat completion, Create completion and Create embedding. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from OpenAI to Mindstamp?
Yes. When something happens in OpenAI, your agent can act in Mindstamp too. This page covers both directions: OpenAI's triggers and Mindstamp's actions are listed here as well.
Do I have to build a connector for Mindstamp 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 Mindstamp 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.