Integration
Connect Cursion and OpenAI
When New Flow fires in Cursion, your agent runs Create message in OpenAI, or New batch in OpenAI to Create Page in Cursion. 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 Cursion and OpenAI to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiAny 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)Example flows
What Cursion and OpenAI can do together
From Cursion to OpenAI
When New Flow in Cursion
then Create message in OpenAI
When New Page in Cursion
then Create assistant in OpenAI
From OpenAI to Cursion
When New batch in OpenAI
then Create Page in Cursion
When New file in OpenAI
then Add case in Cursion
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 Cursion and OpenAI
Triggers and actions 10 triggers · 86 actions
Trigger
New FlowTriggers when a new Flow is created in your Cursion account.
Trigger
New PageTriggers when a new page is added to a Cursion site.
Trigger
New ScanTriggers when a new Scan is created for the selected Cursion page.
Trigger
New SiteTriggers when a new site is added to your Cursion account.
Trigger
New TestTriggers when a new Test (a comparison of two scans) is created for a page.
Action
Add caseGenerates a new test case for a site from a plain-language prompt and returns the process tracking its creation.
Action
Add flowCreates a Flow in Cursion — a named sequence of steps (scans, cases, alerts) that FlowRuns execute.
Action
Create CaseRunRuns a saved Case against a Site, creating a CaseRun that executes in the background and returns immediately.
Action
Create FlowRunRuns a Flow against a Site and returns the new FlowRun, which completes asynchronously.
Action
Create PageCreates a Page under a Cursion Site and, unless skipped, starts its initial baseline Scan.
Action
Create ScanStarts a new Scan of a Site's pages in Cursion. The scan runs in the background and may take several minutes to complete.
Action
Create SiteCreates a Site in Cursion for a domain, then crawls it for pages and runs initial baseline scans in the background.
Action
Delete siteDeletes a site and, with it, all of the site's scans, tests, schedules and alerts.
Action
Get FlowRunReturns a single FlowRun — the result of running a Flow against a Site — including its nodes, status and logs.
Action
Get scanReturns a single Cursion scan with its HTML, logs, Lighthouse and security scores, and screenshots.
Action
Get siteReturns a single Cursion site with its URL, tags, crawl times and latest scan and test summary.
Action
Get testReturns a single Test, the comparison of two scans of a page, with its scores, status and deltas.
Action
List flowsReturns the flows in your Cursion account, including each flow's steps (nodes) and connections (edges).
Action
List pagesReturns the pages that belong to a Cursion site, with each page's URL, tags and latest scan and test results.
Action
List scansReturns the scans captured for a Cursion page, ordered by creation time.
Action
List sitesReturns the sites in your Cursion account, newest first, with each site's URL, tags and latest scan and test details.
Action
List testsReturns the Tests run against a Cursion Page, ordered by creation time.
Trigger
New batchList your organization's batches.
Trigger
New fileReturns a list of files.
Trigger
New modelLists the currently available models.
Trigger
New vector storeReturns a list of vector stores.
Trigger
New videoList recently generated videos for the current project.
Action
Cancel batchCancels an in-progress batch.
Action
Cancel runCancels a run that is in_progress.
Action
Cancel vector store file batchCancel a vector store file batch.
Action
Content moderationClassifies text for hate, harassment, self-harm, sexual, and violence categories using the Moderations API.
Action
Count input tokensReturns input token counts of the request.
Action
Create assistantCreate an assistant with a model and instructions.
Action
Create chat completionSends a list of chat messages to a model via the Chat Completions API and returns the assistant's reply.
Action
Create completionCreates a completion for the provided prompt and parameters.
Action
Create embeddingGenerates a vector embedding for input text using an embeddings model (e.g. text-embedding-3-small).
Action
Create messageCreate a message.
Action
Create runCreate a run.
Action
Creates and executes a batch from an uploaded file of requestsCreates and executes a batch from an uploaded file of requests
Action
Create threadCreate a thread.
Action
Create thread and runCreate a thread and run it in one request.
Action
Create vector storeCreate a vector store.
Action
Create vector store fileCreate a vector store file by attaching a File to a vector store.
Action
Create vector store file batchCreate a vector store file batch.
Action
Create video edit jobCreate a new video generation job by editing a source or existing generated video.
Action
Create video extensionCreate an extension of a completed video.
Action
Create video generation jobCreate a new video generation job from a prompt and optional reference assets.
Action
Create video remixCreate a remix of a completed video using a refreshed prompt.
Action
Delete assistantDelete an assistant.
Action
Delete eval runDelete an eval run.
Action
Delete fileDelete a file and remove it from all vector stores.
Action
Delete messageDeletes a message.
Action
Delete threadDelete a thread.
Action
Delete vector storeDelete a vector store.
Action
Delete vector store fileDelete a vector store file (removes from store, file itself not deleted).
Action
Delete videoPermanently delete a completed or failed video and its stored assets.
Action
Download video contentDownload the generated video bytes or a derived preview asset.
Action
Edit imageCreates an edited or extended image given one or more source images and a prompt.
Action
Generate imageGenerates an image from a text prompt using gpt-image-1 / DALL-E and returns the image URL or base64 data.
Action
Generate speechConverts text into spoken audio using a TTS model and the selected voice. Returns audio bytes.
Action
Get assistantRetrieves an assistant.
Action
Get batchRetrieves a batch.
Action
Get fileReturns information about a specific file.
Action
Get file contentReturns the contents of the specified file.
Action
Get messageRetrieve a message.
Action
Get modelRetrieves a model instance.
Action
Get runRetrieves a run.
Action
Get run stepRetrieves a run step.
Action
Get threadRetrieves a thread.
Action
Get vector storeRetrieves a vector store.
Action
Get vector store fileRetrieves a vector store file.
Action
Get vector store file batchRetrieves a vector store file batch.
Action
Get vector store file contentRetrieve the parsed contents of a vector store file.
Action
Get videoFetch the latest metadata for a generated video.
Action
List conversation itemsList all items for a conversation with the given ID.
Action
List filesLists files that have been uploaded to your OpenAI account.
Action
List messagesReturns a list of messages for a given thread.
Action
List modelsLists the models currently available to your account.
Action
List runsReturns a list of runs belonging to a thread.
Action
List run stepsReturns a list of run steps belonging to a run.
Action
List vector store file batch filesReturns a list of vector store files in a batch.
Action
List vector store filesReturns a list of vector store files.
Action
OpenAI agent messageRuns 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.
Action
Retrieve responseRetrieves a previously created model response by its Response ID.
Action
Search vector storeSearch a vector store for relevant chunks based on a query and filter.
Action
Send model a messageSends 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.
Action
Submit tool outputs to runSubmit tool outputs when a run requires action.
Action
Transcribe audioTranscribes audio into the input language.
Action
Translate audioTranslates audio into English.
Action
Update assistantModifies an assistant.
Action
Update messageModifies a message.
Action
Update runModifies a run.
Action
Update threadModifies a thread.
Action
Update vector storeModifies a vector store.
Action
Update vector store file attributesUpdate attributes on a vector store file.
Action
Upload fileUpload 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 Cursion
Cursion to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Cursion to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Cursion to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Cursion to Google SheetsGoogle Sheets
Cursion to GmailGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Cursion to Google CalendarGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
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
Cursion and OpenAI, answered
What can start an automation from Cursion?
Any of Cursion's 5 triggers in the catalog, including New Flow, New Page, New Scan and New Site. Describe the moment in plain language and your agent picks the right one.
What can your agent do in OpenAI when something happens in Cursion?
Any of OpenAI's 69 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 Cursion?
Yes. When something happens in OpenAI, your agent can act in Cursion too. This page covers both directions: OpenAI's triggers and Cursion's actions are listed here as well.
Do I have to build a connector for Cursion 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.
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.