--- title: "Connect Amazon S3 and Amazon SageMaker - APIANT.ai" description: "When \"New Bucket\" fires in Amazon S3, your agent runs \"Invoke Endpoint\" in Amazon SageMaker." canonical: "https://apiant.ai/connect/amazon-s3-to-amazon-sagemaker" --- # Connect Amazon S3 and Amazon SageMaker When **New Bucket** fires in [Amazon S3](https://apiant.ai/connections/amazon-s3), your agent runs **Invoke Endpoint** in [Amazon SageMaker](https://apiant.ai/connections/amazon-sagemaker), or **New Training Job** in Amazon SageMaker to **Upload File** in Amazon S3. Describe the whole flow and it is built, tested on every scenario and kept running. Amazon S3 **2** triggers Amazon S3 **4** actions Amazon SageMaker **1** trigger Amazon SageMaker **1** action What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Amazon S3 and Amazon SageMaker 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 Amazon S3 and Amazon SageMaker can do together ### From Amazon S3 to Amazon SageMaker - When **New Bucket** in Amazon S3 then **Invoke Endpoint** in Amazon SageMaker ### From Amazon SageMaker to Amazon S3 - When **New Training Job** in Amazon SageMaker then **Upload File** in Amazon S3 - When **New Training Job** in Amazon SageMaker then **Create Bucket** in Amazon S3 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 Amazon S3 and Amazon SageMaker ## Triggers and actions 3 triggers · 5 actions - Trigger **New Bucket** Triggers when a new bucket is created in the connected Amazon S3 account. - Trigger **New or Updated File** Triggers when a file is added to, or changed in, an Amazon S3 bucket, optionally only under a folder prefix. - Action **Create Bucket** Creates a new Amazon S3 bucket in the connected account's region. - Action **Create Text Object** Creates a text file in an Amazon S3 bucket from content you supply, replacing any file already at that path. - Action **Get Object** Returns a file (object) stored in an Amazon S3 bucket, with its text content, type, size and last-modified time. - Action **Upload File** Uploads a file from a URL, such as an attachment from an earlier step, into an Amazon S3 bucket. - Trigger **New Training Job** Triggers when a new SageMaker training job is created. - Action **Invoke Endpoint** Sends input to a deployed Amazon SageMaker model endpoint and returns its prediction. ## Each app on its own - [ **Amazon S3** Amazon Simple Storage Service is a fully redundant data storage system.](https://apiant.ai/connections/amazon-s3) - [ **Amazon SageMaker** Amazon SageMaker is a cloud platform for building, training, and deploying machine learning models at scale](https://apiant.ai/connections/amazon-sagemaker) Reviews ## What our customers say ## More from Amazon S3 - [ **Amazon S3 to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/amazon-s3-to-hubspot) - [ **Amazon S3 to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/amazon-s3-to-salesforce) - [ **Amazon S3 to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/amazon-s3-to-slack) - [ **Amazon S3 to Google Sheets** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/amazon-s3-to-google-sheets) - [ **Amazon S3 to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/amazon-s3-to-gmail) - [ **Amazon S3 to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/amazon-s3-to-google-calendar) ## More into Amazon SageMaker - [ **ActiveCampaign to Amazon SageMaker** ActiveCampaign is a marketing automation, email marketing, and CRM platform.](https://apiant.ai/connect/activecampaign-to-amazon-sagemaker) - [ **Airtable to Amazon SageMaker** Organize anything with Airtable, a modern database created for everyone.](https://apiant.ai/connect/airtable-to-amazon-sagemaker) - [ **2Chat to Amazon SageMaker** 2Chat is a conversational commerce automation tool for WhatsApp, Instagram, Messenger, and SMS.](https://apiant.ai/connect/2chat-to-amazon-sagemaker) - [ **3Scribe to Amazon SageMaker** 3Scribe is the most accurate, automated text transcription available.](https://apiant.ai/connect/3scribe-to-amazon-sagemaker) - [ **5pm to Amazon SageMaker** 5pm is an online project management tool for teams.](https://apiant.ai/connect/5pm-to-amazon-sagemaker) - [ **Abyssale to Amazon SageMaker** Abyssale is a banner maker platform that helps you to automatically generate on-brand images at scale.](https://apiant.ai/connect/abyssale-to-amazon-sagemaker) Questions ## Amazon S3 and Amazon SageMaker, answered ### ### What can start an automation from Amazon S3? Any of Amazon S3's 2 triggers in the catalog, including New Bucket and New or Updated File. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Amazon SageMaker when something happens in Amazon S3? Any of Amazon SageMaker's 1 action, including Invoke Endpoint. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Amazon SageMaker to Amazon S3? Yes. When something happens in Amazon SageMaker, your agent can act in Amazon S3 too. This page covers both directions: Amazon SageMaker's triggers and Amazon S3's actions are listed here as well. ### ### Do I have to build a connector for Amazon S3 or Amazon SageMaker? 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 Amazon S3 and Amazon SageMaker 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.