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

If your image workflow already starts in the terminal, switching to a browser just to generate or edit visuals breaks your flow. NanoBanana MCP gives Claude Code a direct way to create and edit images from a command-line session, so you can describe the change you want, keep the context in your project, and receive an image-oriented result without leaving the tool you are already using.

What you can do

The NanoBanana MCP integration is useful when the task is not just “make an image,” but “understand these inputs and make a coherent visual change.” The source documentation highlights that NanoBanana is built around Gemini image understanding, which makes it suitable for workflows such as taking an object from one image and placing it naturally into another scene.

  • Generate an image from a text prompt using nanobanana_generate_image.
  • Edit an existing image using nanobanana_edit_image.
  • Use multiple image URLs as input for composition tasks.
  • Ask Claude Code to remove unwanted text or watermarks and fill the background.
  • Create small product, documentation, or error-page illustrations from natural language.

How it works

Claude Code talks to NanoBanana through an MCP server. In practice, you add a named MCP server called nanobanana, point it at the Ace Data Cloud MCP endpoint, and pass your Ace Data Cloud API token as an authorization header. Once connected, Claude Code can expose NanoBanana tools inside your coding session.

The MCP endpoint used by the document is:

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

The two tools documented for this server are:

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

Configure NanoBanana MCP in Claude Code

After you have an Ace Data Cloud API token, run the following command in the project where you want Claude Code to use NanoBanana. Replace YOUR_API_TOKEN with your token.

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

One small detail matters: the header flag must be uppercase -H. Lowercase -h is interpreted as help, not as a request header.

Without an explicit scope, Claude Code uses the local scope. That is fine for a one-off experiment, but for real work it is worth choosing the scope deliberately:

  • local: the default. It applies only in the current project directory and is stored in ~/.claude.json.
  • user: use -s user to make the server available globally across projects. It is also stored in ~/.claude.json.
  • project: use -s project to write the configuration to .mcp.json in the project root, which can be shared with a team.

For a personal workstation, I usually prefer -s user. For a repository where the team should share the same MCP setup, -s project is more transparent, but do not commit real tokens to a public repository. Use local secret placeholders instead.

Verify the connection

Once the server is added, run:

claude mcp list

The expected result is that nanobanana appears as connected. The documentation describes this as ✓ Connected. If it does not show up, first check the endpoint URL, the uppercase -H flag, and whether the authorization header is present.

Use case 1: compose two images

The most interesting part of NanoBanana MCP is multi-image editing. Instead of describing everything from scratch, you can provide two image URLs and tell Claude Code how the relationship should work. For example:

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

This is the kind of task where image understanding matters. You are not asking for a generic phone on a generic desk; you are asking the model to preserve the object from one source and integrate it into another scene.

Use case 2: clean up a screenshot

Another practical workflow is removing unwanted text from an image. The source document gives a direct example: remove a text watermark in the bottom-right corner and fill the background. In a Claude Code session, that can be phrased naturally:

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

This is useful for internal docs, mockups, and screenshots where the visual concept is right but one distracting element needs to go away.

Use case 3: generate a small page illustration

NanoBanana MCP can also generate an illustration from a prompt. The document’s example is a 404-page visual:

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

That fits well into a builder workflow: create a placeholder illustration, drop it into a page, then iterate from the terminal while the implementation context is still nearby.

A practical setup pattern

For a small team, a clean pattern is to commit a project-level MCP configuration using placeholders, then have each developer provide their token locally. The important boundary is that the endpoint and server name can be shared, while credentials should stay outside the repository.

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

After that, each developer can replace YOUR_LOCAL_TOKEN_PLACEHOLDER with their own token in a local setup. This keeps the workflow reproducible without putting secrets into .mcp.json.

Wrapping up

NanoBanana MCP is a good fit when you want image generation and editing to live inside the same terminal workflow as the rest of your project. The key pieces are simple: add the nanobanana MCP server, use the documented endpoint, pass the authorization header correctly, verify it with claude mcp list, and then call image generation or editing through Claude Code in natural language.

For the original setup notes and tool list, read the Claude Code integration with NanoBanana MCP documentation.

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