How to Use NanoBanana MCP in Claude Code for Practical Image Editing Workflows

How to Use NanoBanana MCP in Claude Code for Practical Image Editing Workflows

Image work often becomes the awkward step in a developer workflow: you are already in the terminal writing docs, release notes, landing pages, or UI states, but editing a product image still sends you out to a browser and a separate tool. NanoBanana MCP gives Claude Code a way to call image generation and multi-image editing from the same terminal session.

What you can do

The Ace Data Cloud document describes NanoBanana as an MCP server for image generation, image editing, and image composition inside Claude Code. The interesting part is not only text-to-image generation, but image understanding: you can pass multiple image URLs and ask the model to reason about how objects, scenes, lighting, and layout should relate to each other.

In practical terms, this is useful when you want to:

  • compose two images, such as placing an object from one image into the scene of another;
  • remove unwanted text or a watermark-like visual element from a screenshot by filling the background;
  • generate small page illustrations, such as a 404 page graphic, without leaving Claude Code;
  • keep image tasks near the README, docs, or code changes that motivated them.

The documented tools exposed by the MCP server are nanobanana_generate_image for text-to-image generation and nanobanana_edit_image for image editing with support for multiple image inputs.

How it works

Claude Code can connect to an MCP server over HTTP. For NanoBanana, the server URL in the documentation is:

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

Authentication is provided through an HTTP header. The docs explicitly call out that -H must be uppercase in the Claude Code command, because lowercase -h means --help. The token should be kept out of public repositories, issues, screenshots, and chat logs; use a placeholder such as YOUR_ACEDATACLOUD_API_KEY in examples.

Choose the right configuration scope

The same server can be added at three scopes. The choice matters because it controls where Claude Code writes the configuration and who can reuse it.

Local scope for one project

Use -s local when you want to try NanoBanana only in the current project directory. The document says Claude Code writes this into the local ~/.claude.json together with the current project path.

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

User scope for repeated use

If you expect to use image editing across several repositories, use -s user. The document describes this as a user-level configuration in ~/.claude.json, so future projects opened with Claude Code can see the server.

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

Project scope for a team repository

Use -s project when a private project should carry the MCP configuration for teammates. The configuration is written into .mcp.json in the project root. The important operational rule is to avoid committing a real token to a public repository; keep only placeholders or ask each teammate to add credentials locally.

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

When Claude Code reads a project-level MCP configuration for the first time, it may show Pending approval. That is expected: you need to confirm trust for that project configuration inside the Claude Code session.

Verify the connection before asking for images

After adding the server, verify the handshake before you start debugging prompts. Run:

claude mcp list

If nanobanana shows ✓ Connected, the server is reachable. If it does not, the document recommends checking the token, the service URL, and the configuration scope. Avoid relying on old client screenshots or fixed tool counts; the current connection state is what matters.

Practical workflows to try

A good first task is image composition. In Claude Code, you can describe the relationship between two images rather than manually explaining layers. The documentation gives this style of 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.

For documentation cleanup, try an edit request that removes unwanted text from an image while preserving the background:

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

For product pages or error states, you can also ask for 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.

The builder-friendly pattern is simple: keep the visual task next to the code or docs task that created it. If you are updating a README, Claude Code can understand the surrounding context, call nanobanana_generate_image or nanobanana_edit_image, then help you place the resulting asset in the right documentation section.

Where this fits

NanoBanana MCP is most useful when image work is part of a development loop rather than a standalone design session. You still need to review the output like any other generated artifact, but you no longer have to break context just to request a composition, cleanup, or small illustration.

For the original setup details, scopes, verification command, and documented tool names, read the Ace Data Cloud guide: 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