
Generate images, video, and 20+ edits from any MCP client — billed to your imageat credits.
Pick an idea, preview the result, and send the complete prompt to Claude with imageat MCP.
You'll paste this into the custom-connector dialog in the next step.
https://mcp.imageat.com/mcp
Add a custom connector, name it “imageat”, paste the URL above, and leave OAuth fields empty.
Claude opens imageat in your browser — sign in and click Allow. No API key to copy. Usage is billed to your credits; a “Claude (MCP)” key appears on your Projects page (revoke anytime).
Nano Banana Pro, GPT Image 2, Seedream & more — 1K–4K.
Veo, Kling, Seedance — text-to-video and image-to-video.
Remove background, relight, virtual try-on, object eraser…
Read your balance before running a job.
Stay in the conversation. imageat turns your prompt and references into a finished visual, then returns it to your AI client.
Ask your agent for a product photo, a portrait, or a scene in plain language. It picks the right model and resolution — no prompt engineering required.

Generate a still, animate it, then refine the result without leaving the conversation.













We've answered the most frequently asked ones.
It's a Model Context Protocol server that gives AI clients — Claude, ChatGPT, Cursor, OpenClaw, Hermes, and others — tools to generate images, generate video, and run imageat's editing features. Every call is billed against your imageat account credits, same as generating on the site.
claude.ai, ChatGPT, and OpenClaw: add the connector and sign in — no key to paste. Claude Desktop, Cursor, and Hermes: grab an API key from Projects and add it to your config.
Full setup, tools, and error codes in the API documentation.
SAvailable onSmithery