How to Use NanoBanana MCP from Claude Code for Image Editing Workflows

How to Use NanoBanana MCP from Claude Code for Image Editing Workflows

If your coding agent can already read files, run commands, and help you refactor code, the next useful step is letting it produce the visual assets that usually interrupt your flow: README screenshots, product mockups, 404 illustrations, and small image edits for docs or release notes.

What you can do

The NanoBanana MCP setup described in the Ace Data Cloud documentation connects Claude Code to a managed MCP server for image generation and image editing. The interesting part is not only text-to-image. The documented workflow emphasizes image understanding: you can provide multiple image URLs and ask the model to combine, reposition, or clean up elements in a way that respects the scene.

Once configured, Claude Code can call two documented tools:

  • nanobanana_generate_image for text-to-image generation.
  • nanobanana_edit_image for image editing, including multiple image inputs.

That makes the integration practical for builder workflows where the agent already has project context. For example, while updating a landing page or README, you can ask Claude Code to generate a missing illustration, remove unwanted text from an image, or place an object from one reference image into the scene of another.

How it works

The integration uses a remote MCP server:

https://nanobanana.mcp.acedata.cloud/mcp

Claude Code connects to that server over HTTP. Authentication is passed with an uppercase -H header flag:

-H "Authorization: Bearer YOUR_ACEDATACLOUD_API_KEY"

The uppercase detail matters because the documentation calls out that lowercase -h is interpreted as --help. In practice, most setup issues come from one of three places: an incorrect token, the wrong service URL, or using the wrong configuration scope for the way you want to work.

Choose the right Claude Code scope

The docs show three ways to register the MCP server. Use local when you only want the current project to see the server:

claude mcp add nanobanana --transport http https://nanobanana.mcp.acedata.cloud/mcp   -H "Authorization: Bearer YOUR_ACEDATACLOUD_API_KEY"   -s local

Use user if you regularly want NanoBanana available across projects:

claude mcp add nanobanana --transport http https://nanobanana.mcp.acedata.cloud/mcp   -H "Authorization: Bearer YOUR_ACEDATACLOUD_API_KEY"   -s user

Use project when a team wants a project-level MCP configuration in the repository:

claude mcp add nanobanana --transport http https://nanobanana.mcp.acedata.cloud/mcp   -H "Authorization: Bearer YOUR_ACEDATACLOUD_API_KEY"   -s project

The project scope writes configuration into .mcp.json in the project root. That is useful for private team repositories, but the real token should not be committed to public repositories. If the project-level config is read for the first time, Claude Code may show Pending approval; according to the documentation, that is a normal trust prompt for the project configuration.

Verify the connection before asking for images

After adding the server, verify the handshake:

claude mcp list

A working setup should show nanobanana as ✓ Connected. If it does not, debug the basics first: confirm the token value, confirm that the URL is exactly https://nanobanana.mcp.acedata.cloud/mcp, and confirm that you added the server at the scope where your current Claude Code session can see it.

Use case 1: compose multiple images

One practical workflow is image composition. Suppose you have a product photo and a separate room or desk scene. The documented example is to ask Claude Code to place the object from one image into the scene of another:

Place the phone from the first image onto the desk in the second image, adjusting the angle and lighting to make it look natural.

This is useful when you need contextual images for docs, changelogs, app store assets, or a quick product concept. The point is to keep the task inside the terminal session where Claude Code already understands what you are building.

Use case 2: clean screenshots and assets

Another common builder task is removing text that should not appear in a public asset. The documentation gives a simple natural-language pattern:

Edit this image to remove the text watermark in the lower right corner, filling it with the background.

For tutorials, this can help clean screenshots before they go into a README or blog post. For product work, it can help remove placeholder copy or accidental labels from a mockup before sharing it with a team.

Use case 3: generate small illustrations for UI states

NanoBanana MCP can also be used for new illustrations. The docs include this example:

Generate an illustration of a small dinosaur squatting next to a crack in the ground looking down, to be used for a 404 page.

That is the kind of small, contained visual task that pairs well with Claude Code. You can be editing the route, error copy, or component styles, then ask the agent to create a matching illustration without switching into a separate creative tool.

A practical setup checklist

  1. Create or copy an Ace Data Cloud API token from the console and keep it out of public screenshots, issues, and repositories.
  2. Add the MCP server with claude mcp add nanobanana, the HTTP transport, and the documented service URL.
  3. Choose -s local, -s user, or -s project based on whether this is a trial, a personal global setup, or a team project setup.
  4. Run claude mcp list and confirm ✓ Connected.
  5. Start with a low-risk prompt such as generating a 404 illustration or cleaning a non-sensitive screenshot.

The cleanest way to think about NanoBanana MCP in Claude Code is as a visual helper inside your existing builder loop. It is not a replacement for design judgment, but it removes the friction between writing code, preparing documentation, and producing the small visual assets that make a project easier to understand. For the exact setup commands and related notes, read the Ace Data Cloud documentation: Claude Code with Nano Banana MCP.

Comments

Post a Comment

Popular posts from this blog

Artistic QR Code API Integration Guidance

Image
Artistic QR code is an innovative technological product that combines QR codes with beautiful background images, creating practical and visually appealing works. They not only possess the functionality of traditional QR codes, allowing quick scanning and recognition by smart devices, but also incorporate artistic elements to enhance visual appeal and brand recognition. Some artistic QR codes are even generated by artificial intelligence, fully leveraging modern technology to demonstrate unparalleled innovation and uniqueness. This makes artistic QR codes widely applicable in areas such as brand marketing and advertising. In simple terms, artistic QR codes are the perfect combination of QR code scanning and artistic aesthetics. They not only provide the function of information transmission, but also enhance the user's visual experience, making each scan a delightful artistic enjoyment. Overview of Artworks Let's take a look at a few QR code works: How are they? These are ar...
Read more

How to Configure Claude Code with CC Switch and Ace Data Cloud

Image
If you use Claude Code across a terminal, VS Code, or remote development setup, the awkward part is often not the model itself but the configuration: where should requests go, where should the token live, and how do you switch providers without editing files by hand? This guide walks through a practical setup using CC Switch as the graphical configuration manager and Ace Data Cloud as the Anthropic-compatible base URL. The goal is simple: configure Claude Code once, verify the active endpoint, and keep the setup easy to change later. What you can do With the setup described in the Ace Data Cloud documentation, you can: Manage Claude Code provider configuration through a desktop UI instead of manually editing settings.json . Store an Ace Data Cloud provider with ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN . Switch the active Claude Code provider from CC Switch without rewriting your configuration every time. Use the same provider configuration from the terminal an...
Read more

How to Build a Server-Side Image Editing Workflow with GPT-Image-2

Image
If your product needs image editing, the hard part is rarely the model call itself. The real challenge is building a reliable workflow around user images, reference assets, predictable output sizes, and slow-running jobs without forcing every file through a manual upload step. This guide walks through a practical server-side workflow using the OpenAI Images Edits API on Ace Data Cloud. The focus is gpt-image-2 , because the documented editing flow supports direct image URLs, base64 input, multiple reference images, high-resolution output through size , and asynchronous callbacks. What you can do The edits endpoint is designed for turning one or more input images plus an instruction into a modified output image. In practical terms, you can use it to: Convert an existing infographic or poster into a different visual theme while preserving its layout. Change a product, shelf, room, or object style while keeping the original arrangement stable. Pass image URLs directly f...
Read more