--- title: "Connect GPTBots to Amazon Rekognition - APIANT.ai" description: "When \"New message received\" fires in GPTBots, your agent runs \"Check Image for Unsafe Content\" in Amazon Rekognition." canonical: "https://apiant.ai/connect/gptbots-to-amazon-rekognition" --- # Connect GPTBots to Amazon Rekognition When **New message received** fires in [GPTBots](https://apiant.ai/connections/gptbots), your agent runs **Check Image for Unsafe Content** in [Amazon Rekognition](https://apiant.ai/connections/amazon-rekognition). Describe the whole flow and it is built, tested on every scenario and kept running. GPTBots **1** trigger GPTBots **7** actions Amazon Rekognition **4** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want GPTBots and Amazon Rekognition 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 GPTBots can start in Amazon Rekognition - When **New message received** in GPTBots then **Check Image for Unsafe Content** in Amazon Rekognition - When **New message received** in GPTBots then **Detect Faces in Image** in Amazon Rekognition 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 GPTBots and Amazon Rekognition ## Triggers and actions 1 trigger · 11 actions - Trigger **New message received** Fires when GPTBots delivers a new agent/user message via its "Webhook receives messages" mechanism under Agent API. Delivery mechanism (service webhook URL vs manual registration) needs confirming against the vendor docs at build time. - Action **Create Agent Conversation** Create an Agent conversation. - Action **Get conversation** Fetch a single conversation's detail by conversation ID. - Action **List conversations** List conversations for an agent, paginated. - Action **List documents** List documents in a knowledge base. - Action **List knowledge bases** List knowledge bases in the workspace. - Action **Run Workflow** Run an GPTBots workflow. - Action **Send Agent Message** Send a message to an Agent. - Action **Check Image for Unsafe Content** Checks an image stored in S3 for explicit, violent or otherwise unsafe content and returns any moderation labels found. - Action **Detect Faces in Image** Finds the faces in an image stored in S3 and returns, for each, its estimated age range, emotions and attributes such as glasses or a smile. - Action **Detect Objects and Scenes in Image** Returns the objects, scenes and concepts found in an image stored in S3, each with a confidence score. - Action **Detect Text in Image** Reads the words and lines of text that appear in an image stored in S3. ## Each app on its own - [ **GPTBots** GPTBots seamlessly connect LLMs with enterprise data, services and workflows, empower your business with...](https://apiant.ai/connections/gptbots) - [ **Amazon Rekognition** Cloud API for image and video analysis, including face detection, object/scene recognition, and text...](https://apiant.ai/connections/amazon-rekognition) Reviews ## What our customers say ## More from GPTBots - [ **GPTBots to Gumlet** Gumlet is best way to stream ad-free videos on internet.](https://apiant.ai/connect/gptbots-to-gumlet) - [ **GPTBots to MailChannels** MailChannels is a service that facilitates sending emails with anti-spam protection.](https://apiant.ai/connect/gptbots-to-mailchannels) - [ **GPTBots to Newton** Newton is a symbolic and arithmetic mathematics engine exposed over HTTP.](https://apiant.ai/connect/gptbots-to-newton) - [ **GPTBots to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/gptbots-to-hubspot) - [ **GPTBots to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/gptbots-to-salesforce) - [ **GPTBots to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/gptbots-to-slack) ## More into Amazon Rekognition - [ **HubSpot to Amazon Rekognition** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-amazon-rekognition) - [ **Salesforce to Amazon Rekognition** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-amazon-rekognition) - [ **Slack to Amazon Rekognition** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-amazon-rekognition) - [ **Google Sheets to Amazon Rekognition** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-amazon-rekognition) - [ **Gmail to Amazon Rekognition** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-amazon-rekognition) - [ **Google Calendar to Amazon Rekognition** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-amazon-rekognition) Questions ## GPTBots and Amazon Rekognition, answered ### ### What can start an automation from GPTBots? Any of GPTBots's 1 trigger in the catalog, including New message received. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Amazon Rekognition when something happens in GPTBots? Any of Amazon Rekognition's 4 actions, including Check Image for Unsafe Content, Detect Faces in Image, Detect Objects and Scenes in Image and Detect Text in Image. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Amazon Rekognition to GPTBots? Amazon Rekognition has no triggers in the catalog today, so automations start in GPTBots. If you need the other direction, ask: your agent reads Amazon Rekognition's API documentation and adds it. ### ### Do I have to build a connector for GPTBots or Amazon Rekognition? 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 GPTBots and Amazon Rekognition 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.