--- title: "Connect OpenAI to Anchor (Agentic Browser Automation) - APIANT.ai" description: "When \"New batch\" fires in OpenAI, your agent runs \"Create Task\" in Anchor (Agentic Browser Automation)." canonical: "https://apiant.ai/connect/openai-to-anchor-agentic-browser-automation" --- # Connect OpenAI to Anchor (Agentic Browser Automation) When **New batch** fires in [OpenAI](https://apiant.ai/connections/openai), your agent runs **Create Task** in [Anchor (Agentic Browser Automation)](https://apiant.ai/connections/anchor-agentic-browser-automation). Describe the whole flow and it is built, tested on every scenario and kept running. OpenAI **5** triggers OpenAI **69** actions Anchor (Agentic Browser Automation) **31** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want OpenAI and Anchor (Agentic Browser Automation) to do together? Give your AI client this address. `https://mcp.apiant.ai` One 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.ai` Start Claude Code there, approve the server, and sign in in the browser page it opens. [Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code) ### 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)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) ### Zed Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) ### 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)](https://apiant.ai/docs/mcp) Example flows ## What OpenAI can start in Anchor (Agentic Browser Automation) - When **New batch** in OpenAI then **Create Task** in Anchor (Agentic Browser Automation) - When **New file** in OpenAI then **Agent Task** in Anchor (Agentic Browser Automation) 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 OpenAI and Anchor (Agentic Browser Automation) ## Triggers and actions 5 triggers · 100 actions - Trigger **New batch** List your organization's batches. - Trigger **New file** Returns a list of files. - Trigger **New model** Lists the currently available models. - Trigger **New vector store** Returns a list of vector stores. - Trigger **New video** List recently generated videos for the current project. - Action **Cancel batch** Cancels an in-progress batch. - Action **Cancel run** Cancels a run that is in_progress. - Action **Cancel vector store file batch** Cancel a vector store file batch. - Action **Content moderation** Classifies text for hate, harassment, self-harm, sexual, and violence categories using the Moderations API. - Action **Count input tokens** Returns input token counts of the request. - Action **Create assistant** Create an assistant with a model and instructions. - Action **Create chat completion** Sends a list of chat messages to a model via the Chat Completions API and returns the assistant's reply. - Action **Create completion** Creates a completion for the provided prompt and parameters. - Action **Create embedding** Generates a vector embedding for input text using an embeddings model (e.g. text-embedding-3-small). - Action **Create message** Create a message. - Action **Create run** Create a run. - Action **Creates and executes a batch from an uploaded file of requests** Creates and executes a batch from an uploaded file of requests - Action **Create thread** Create a thread. - Action **Create thread and run** Create a thread and run it in one request. - Action **Create vector store** Create a vector store. - Action **Create vector store file** Create a vector store file by attaching a File to a vector store. - Action **Create vector store file batch** Create a vector store file batch. - Action **Create video edit job** Create a new video generation job by editing a source or existing generated video. - Action **Create video extension** Create an extension of a completed video. - Action **Create video generation job** Create a new video generation job from a prompt and optional reference assets. - Action **Create video remix** Create a remix of a completed video using a refreshed prompt. - Action **Delete assistant** Delete an assistant. - Action **Delete eval run** Delete an eval run. - Action **Delete file** Delete a file and remove it from all vector stores. - Action **Delete message** Deletes a message. - Action **Delete thread** Delete a thread. - Action **Delete vector store** Delete a vector store. - Action **Delete vector store file** Delete a vector store file (removes from store, file itself not deleted). - Action **Delete video** Permanently delete a completed or failed video and its stored assets. - Action **Download video content** Download the generated video bytes or a derived preview asset. - Action **Edit image** Creates an edited or extended image given one or more source images and a prompt. - Action **Generate image** Generates an image from a text prompt using gpt-image-1 / DALL-E and returns the image URL or base64 data. - Action **Generate speech** Converts text into spoken audio using a TTS model and the selected voice. Returns audio bytes. - Action **Get assistant** Retrieves an assistant. - Action **Get batch** Retrieves a batch. - Action **Get file** Returns information about a specific file. - Action **Get file content** Returns the contents of the specified file. - Action **Get message** Retrieve a message. - Action **Get model** Retrieves a model instance. - Action **Get run** Retrieves a run. - Action **Get run step** Retrieves a run step. - Action **Get thread** Retrieves a thread. - Action **Get vector store** Retrieves a vector store. - Action **Get vector store file** Retrieves a vector store file. - Action **Get vector store file batch** Retrieves a vector store file batch. - Action **Get vector store file content** Retrieve the parsed contents of a vector store file. - Action **Get video** Fetch the latest metadata for a generated video. - Action **List conversation items** List all items for a conversation with the given ID. - Action **List files** Lists files that have been uploaded to your OpenAI account. - Action **List messages** Returns a list of messages for a given thread. - Action **List models** Lists the models currently available to your account. - Action **List runs** Returns a list of runs belonging to a thread. - Action **List run steps** Returns a list of run steps belonging to a run. - Action **List vector store file batch files** Returns a list of vector store files in a batch. - Action **List vector store files** Returns a list of vector store files. - Action **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. - Action **Retrieve response** Retrieves a previously created model response by its Response ID. - Action **Search vector store** Search a vector store for relevant chunks based on a query and filter. - Action **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. - Action **Submit tool outputs to run** Submit tool outputs when a run requires action. - Action **Transcribe audio** Transcribes audio into the input language. - Action **Translate audio** Translates audio into English. - Action **Update assistant** Modifies an assistant. - Action **Update message** Modifies a message. - Action **Update run** Modifies a run. - Action **Update thread** Modifies a thread. - Action **Update vector store** Modifies a vector store. - Action **Update vector store file attributes** Update attributes on a vector store file. - Action **Upload file** Upload a file that can be used across various endpoints. - Action **Agent Task** Starts a natural-language browser agent task asynchronously and returns a workflow ID; fetch the outcome with Agent Task Result. - Action **Agent Task Result** Get the result of an async Agent Task execution. - Action **Copy Selected Text** Copy the currently selected text to the clipboard - Action **Create Browser Session** Start a new browser session with customizable configurations - Action **Create Task** Create a new task or update existing task - Action **Delete Profile** Delete a profile - Action **Delete Task** Soft deletes a task and all its versions. - Action **Deploy Task** Deploy a task version - Action **Drag and Drop** Drag and drop operation in the browser - Action **End All Sessions** Terminates all active browser sessions on the account. - Action **End Browser Session** Terminate a specific browser session - Action **Fetch Webpage** Fetches the fully rendered content of a URL through Anchor's Web Unlocker (stealth browser, residential proxy, automatic CAPTCHA solving), without a browser session. - Action **Get Browser Session** Retrieve details of a specific browser session - Action **Get Clipboard** Get clipboard content - Action **Get Profile** Retrieve details of a specific profile - Action **Get Session Downloads** Get session downloads - Action **Get Session Recordings** Retrieve session recordings - Action **Get Task** Retrieves a task's metadata (name, description, latest version, timestamps) without its code. - Action **Keyboard Shortcut** Send a keyboard shortcut to the browser session - Action **Mouse Click** Click at a given coordinate in the browser - Action **Mouse Double Click** Double click at a given coordinate - Action **Mouse Move** Move mouse cursor - Action **Navigate to URL** Navigate to a URL - Action **Paste Text** Paste text - Action **Perform Web Task** Start an AI-powered web task asynchronously using the Tasks API. Returns task execution information. Check execution results using the task execution history endpoint. - Action **Run Task** Execute a task - Action **Scroll** Scroll the page - Action **Set Clipboard** Set clipboard content - Action **Take Screenshot** Captures a Chromium screenshot of a webpage (PNG), optionally inside an existing browser session. - Action **Take Session Screenshot** Take a screenshot of current session - Action **Type Text** Type text with keyboard ## Each app on its own - [ **OpenAI** OpenAI's platform for text generation (Responses + Chat Completions), image generation (gpt-image-1 /...](https://apiant.ai/connections/openai) - [ **Anchor (Agentic Browser Automation)** Anchor (Agentic Browser Automation) is a cloud infrastructure tool for browser automation and control...](https://apiant.ai/connections/anchor-agentic-browser-automation) Reviews ## What our customers say ## More from OpenAI - [ **OpenAI to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/openai-to-hubspot) - [ **OpenAI to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/openai-to-salesforce) - [ **OpenAI to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/openai-to-slack) - [ **OpenAI to Stripe** Stripe is a payment processing platform for online businesses.](https://apiant.ai/connect/openai-to-stripe) - [ **OpenAI to QuickBooks Online** QuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...](https://apiant.ai/connect/openai-to-quickbooks-online) - [ **OpenAI to Pipedrive** Pipedrive is a sales CRM and pipeline management tool.](https://apiant.ai/connect/openai-to-pipedrive) ## More into Anchor (Agentic Browser Automation) - [ **HubSpot to Anchor (Agentic Browser Automation)** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-anchor-agentic-browser-automation) - [ **Salesforce to Anchor (Agentic Browser Automation)** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-anchor-agentic-browser-automation) - [ **Slack to Anchor (Agentic Browser Automation)** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-anchor-agentic-browser-automation) - [ **Google Sheets to Anchor (Agentic Browser Automation)** Google Sheets](https://apiant.ai/connect/google-sheets-to-anchor-agentic-browser-automation) - [ **Gmail to Anchor (Agentic Browser Automation)** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-anchor-agentic-browser-automation) - [ **Google Calendar to Anchor (Agentic Browser Automation)** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-anchor-agentic-browser-automation) Questions ## OpenAI and Anchor (Agentic Browser Automation), answered ### ### What can start an automation from OpenAI? Any of OpenAI's 5 triggers in the catalog, including New batch, New file, New model and New vector store. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Anchor (Agentic Browser Automation) when something happens in OpenAI? Any of Anchor (Agentic Browser Automation)'s 31 actions, including Create Browser Session, Create Task, Agent Task and Agent Task Result. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Anchor (Agentic Browser Automation) to OpenAI? Anchor (Agentic Browser Automation) has no triggers in the catalog today, so automations start in OpenAI. If you need the other direction, ask: your agent reads Anchor (Agentic Browser Automation)'s API documentation and adds it. ### ### Do I have to build a connector for OpenAI or Anchor (Agentic Browser Automation)? 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 OpenAI and Anchor (Agentic Browser Automation) 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.