How to Use NanoBanana MCP in Claude Code for Terminal-Based Image Editing

How to Use NanoBanana MCP in Claude Code for Terminal-Based Image Editing

When image generation is part of your build loop, switching from the terminal to a separate design tool breaks concentration. The NanoBanana MCP Server lets Claude Code call image generation and image editing tools directly from a terminal session, so you can describe the visual change you want while staying inside the project context.

What you can do

The Ace Data Cloud document describes a focused Claude Code workflow for NanoBanana MCP. In practice, it gives you two tools inside Claude Code:

  • nanobanana_generate_image for text-to-image generation.
  • nanobanana_edit_image for image editing, including multi-image input.

The useful part is not only that Claude can request an image. It is that NanoBanana, backed by Gemini image understanding, can reason about image content. The source guide gives a concrete example: provide two images, then ask the model to place an object from image A into the scene of image B while adjusting angle and lighting.

How it works

Claude Code supports MCP servers over HTTP. The NanoBanana MCP Server is exposed at https://nanobanana.mcp.acedata.cloud/mcp. After you add that server to Claude Code with an authorization header, Claude can discover the available NanoBanana tools and call them from your coding session.

The connection is configured with the Claude Code CLI. The documented command is:

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

One small detail matters: the header flag is uppercase -H. The guide explicitly warns that lowercase -h means help, not an HTTP header. If the server does not appear connected, this is the first typo I would check.

Choose the right Claude Code scope

Claude Code can store the MCP configuration at different scopes. The document calls out three options:

  • local, the default when you omit -s, applies only in the current project directory.
  • user, set with -s user, makes the server available globally across projects.
  • project, set with -s project, writes configuration to .mcp.json in the project root so a team can share the setup.

For a single experiment, local scope is fine. For a design-heavy app where image generation is part of everyday work, user scope is convenient. For a team workflow, project scope is attractive, but the guide includes an important caveat: do not commit real tokens to public repositories. Use environment-variable placeholders instead.

Verify the connection before asking for images

After adding the server, run:

claude mcp list

You should see nanobanana marked as connected. I like doing this before the first generation request because it separates connection problems from prompt problems. If the server is not connected, fix the MCP configuration first; if it is connected, then iterate on the image prompt.

Use case 1: compose two images

The most interesting workflow in the document is multi-image composition. Instead of treating every input as a flat reference, nanobanana_edit_image can work with multiple image URLs and understand their relationship. A practical product example might be: take a device from one photo and place it naturally into a desk scene from another.

The guide’s example prompt is direct and specific:

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

That style is worth copying. Tell the model what object to move, which image provides the scene, and what realism constraints matter: angle, lighting, shadows, scale, or background continuity.

Use case 2: clean up screenshots or visual assets

The document also shows a simple editing task: removing unwanted text from an image and filling the background. In a builder workflow, this is useful when preparing documentation screenshots, mockups, or social previews where one visual element distracts from the core UI.

Edit this image to remove the text watermark in the bottom right corner, filling the background

For best results, keep the instruction narrow. If the task is cleanup, do not also ask for a style change, new layout, and color correction in the same request. Make one edit, inspect the result, then continue.

Use case 3: generate small illustrations for product states

NanoBanana MCP can also generate images from text. The source guide gives a 404-page illustration example:

Generate an illustration of a small dinosaur crouching next to a crack in the ground looking down, for use on a 404 page

This is where keeping Claude Code in the loop feels natural. You can ask for an empty-state illustration while looking at the route, component, or copy that will use it. The prompt does not need to be theatrical; it needs to describe the subject, mood, and destination inside the product.

A minimal terminal workflow

Putting the pieces together, a safe first run looks like this:

  1. Copy your Ace Data Cloud API token from the platform.
  2. Add NanoBanana MCP to Claude Code with the documented HTTP endpoint.
  3. Run claude mcp list and confirm nanobanana is connected.
  4. Ask Claude Code for either nanobanana_generate_image or nanobanana_edit_image behavior in natural language.
  5. Iterate in small steps: composition, cleanup, then final polish.
# Add the MCP server for the current project directory
claude mcp add nanobanana --transport http https://nanobanana.mcp.acedata.cloud/mcp   -H "Authorization: Bearer YOUR_TOKEN"

# Confirm Claude Code can see it
claude mcp list

That is enough to start treating image work as part of the development loop rather than a separate browser chore. For the complete setup notes and the original examples, read the Ace Data Cloud documentation: Claude Code integration with NanoBanana 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
Image
Nexior is an open-source project on GitHub that allows us to deploy our AI application site with one click, including AI Q&A, Midjourney drawing, knowledge base Q&A, artistic QR codes, and more. There is no need to develop AI systems, purchase AI accounts, worry about API support, or configure payment systems. It comes with zero startup costs and allows you to earn income through AI without risk. This article will introduce the deployment process of the Nexior project on Vercel. Without any programming skills, you can deploy your AI site in a few minutes and easily generate revenue. Preparation First, open the Nexior GitHub repository at: https://github.com/AceDataCloud/Nexior , then register or log in to your GitHub account. Click Fork to clone the code to your local repository, as shown below: After completing the Fork, we will get our personal repository, as shown below: In this example, the account is Germey, so we can see that we have Forked to the Germey user, wit...
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