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

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

If your development workflow keeps jumping from terminal to browser just to prepare visuals, a hosted MCP image tool can keep more of that work inside Claude Code.

What you can do

The NanoBanana MCP integration for Claude Code is aimed at practical image tasks that benefit from image understanding, not just text-to-image generation. According to the Ace Data Cloud document, NanoBanana uses Google's Gemini model at its core, which makes it useful when the task depends on understanding relationships between images.

In a Claude Code session, the documented tools are:

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

That means you can ask Claude Code to generate a page illustration, remove unwanted text from an image, or combine multiple source images into a new composition while staying in the same terminal-driven workflow.

How it works

The integration uses a remote MCP Server hosted at https://nanobanana.mcp.acedata.cloud/mcp. Claude Code connects to that server over HTTP and sends an authorization header containing your Ace Data Cloud API token.

The important detail is that you are not installing an image model locally. You are adding an MCP server configuration to Claude Code, then letting Claude Code call the exposed tools when your natural-language request needs image generation or editing.

The document describes three configuration scopes: local, user, and project. Choosing the right one matters because it controls where Claude Code writes the MCP configuration and who can reuse it.

Start with a local project configuration

For a first test, use -s local. This binds the configuration to the project directory where you run the command. The documentation says Claude Code writes the record into the local ~/.claude.json, together with the current project path.

Use this when you want to confirm the handshake, try a few prompts, and avoid affecting every Claude Code project on your machine.

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

One small but easy-to-miss detail from the document: -H must be uppercase. The lowercase -h is interpreted as --help, so it will not set your authorization header.

Use user or project scope when the workflow is stable

Once the integration is part of your regular workflow, the documented user scope makes NanoBanana MCP available across projects opened with Claude Code:

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

For team projects, the document also supports -s project. This writes configuration into .mcp.json in the current project root. That can be useful for private repositories where teammates should share the same MCP server definition.

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

Do not commit a real token to a public repository. The document recommends using a placeholder such as YOUR_ACEDATACLOUD_API_KEY in examples, or having each person add their token locally. When Claude Code reads a project-level configuration for the first time, it may show Pending approval; approving trust for that project configuration is expected behavior.

Verify the MCP connection

After adding the server, verify the connection before trying an image task:

claude mcp list

If nanobanana shows ✓ Connected, the handshake is working. If it does not, check the token, the service URL, and the scope you used. The source document explicitly warns against relying on old client versions or fixed historical tool counts to judge the current status.

Try image editing prompts that need visual understanding

The most useful first test is not a generic poster prompt. Try something where the model needs to understand source images. For example, the document gives this style of composition request:

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

That is the kind of task where multi-image input matters: one image provides the object, another provides the scene, and nanobanana_edit_image handles the edit.

For cleanup work, you can ask Claude Code to remove unwanted text from an image:

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

And for product or documentation pages, you can generate a small illustration directly from the terminal:

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

A practical workflow for builders

A simple workflow is: configure with -s local, run claude mcp list, test one image-generation prompt, then test one multi-image edit. If the results are useful across projects, re-add the same server with -s user. If the workflow belongs to a shared private repo, move to -s project and keep the real token out of committed files.

This keeps the product surface area small: Claude Code remains your working environment, while NanoBanana MCP becomes a callable image tool for the moments when code, docs, or product pages need visual assets.

Read the full source document here: 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
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