> ## Documentation Index > Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI Images > Connect OpenAI Images to xpander and give agents its 3 actions: how to sign in and connect it, and which actions to hold for approval. HTTP API connector An HTTP API described by an OpenAPI spec, not an MCP server. Calls go through xpander's function endpoint `https://functions.xpander.ai/openai-images`, which fronts the OpenAI Images API, and carry a credential xpander supplies, so there is nothing to paste. ## What the skill can do API connector: 3 actions, as they appear in the skill panel. 3 of them create, change or delete something in OpenAI Images; mark those under **These actions need approval** when you add the skill to an agent. * **Image editing service** (1): Edit Image with AI * **Image generation service** (1): Generate Image from Text * **Image enhancement service** (1): Improve Image Iteratively ## Connect OpenAI Images In Xpander Chat, open the agent's settings, click **Add skill**, and search for **OpenAI Images**. The connect dialog asks for a connection name and whether the connection is for the **Organization** (one shared account) or **Personal** (your own account, so the agent acts with your permissions where systems allow). On an agent other people use, a personal connection runs their requests as you unless the binding requires each person's own sign-in; see [whose credential a shared agent uses](/use/agents/permissions#whose-credential-a-shared-agent-uses). OpenAI Images connects with **Sign in with OpenAI Images**: you authorize in the browser and xpander stores the OAuth token; the agent never sees it, and the token is attached at the moment a skill is called. Calls go to `https://functions.xpander.ai/openai-images`. ## Give an agent the OpenAI Images skill Once OpenAI Images is connected, any agent you can edit may be given the skill: open the agent's settings, click **Add skill**, and choose **OpenAI Images**. Enable only the action groups the agent needs, and mark the actions that should wait for a named person's sign-off under **These actions need approval**. Which skills exist for your organization, and who may add them, is decided by your admins; see [Skills](/use/skills). ## Related Resources * [Skills](/use/skills)