How to Use NanoBanana MCP in OpenCode for Multi-Image Editing

How to Use NanoBanana MCP in OpenCode for Multi-Image Editing

Multi-image editing becomes much more useful when it can stay inside the same terminal workflow where you are already writing docs, adjusting product copy, or preparing release assets.

What you can do

The NanoBanana MCP server is designed for image generation and image editing workflows inside OpenCode. The documented strengths are practical rather than abstract: product background replacement, virtual try-on, subject-consistent edits for people or objects, and editing one image with another image as a reference.

In an OpenCode session, that means you can ask for tasks such as:

  • placing a product image into a scene while keeping lighting consistent;
  • changing a model image to wear a referenced garment while preserving face and pose;
  • generating a small illustration for a 404 page or documentation page;
  • using several source images as references without leaving the terminal.

How it works

OpenCode reads MCP servers from an opencode.json file. Ace Data Cloud exposes NanoBanana as a remote MCP endpoint, so OpenCode connects to it over HTTPS and passes your Bearer token in the request headers. The important endpoint from the document is:

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

The server provides two main tools in the documentation:

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

The implementation detail that trips people up is authentication. The config must include oauth: false, because this MCP server uses Bearer Token authentication rather than OpenCode's OAuth challenge flow.

Configure the token without leaking it

Start by putting your Ace Data Cloud API token into an environment variable. Do not paste the real token into a repository, issue, screenshot, or shared chat.

export ACEDATACLOUD_API_KEY="replace with your real token"

If you keep variables in a local .env file, make sure they are exported to the OpenCode process. The document notes this pattern:

set -a && source .env && set +a

Without exporting, OpenCode may resolve the header as Authorization: Bearer , which looks like an authentication problem even though the config file shape is correct.

Use a global OpenCode configuration

For a personal machine where you want NanoBanana available across projects, place the MCP config at ~/.config/opencode/opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nanobanana": {
      "type": "remote",
      "url": "https://nanobanana.mcp.acedata.cloud/mcp",
      "enabled": true,
      "oauth": false,
      "headers": { "Authorization": "Bearer {env:ACEDATACLOUD_API_KEY}" }
    }
  }
}

The field meanings are simple: type is remote, url points to the hosted MCP server, enabled turns the server on, oauth disables OAuth handling, and headers.Authorization injects your Bearer token from the environment.

Use a project-level configuration

If a single repository needs this workflow, put the same structure in opencode.json at the project root. The document states that project-level config overrides global config, which is useful for teams or repo-specific tool choices.

When committing a project-level file, keep the placeholder form:

"headers": { "Authorization": "Bearer {env:ACEDATACLOUD_API_KEY}" }

That keeps the config reviewable while leaving the secret on each developer's machine.

Verify the MCP connection

After saving the config, verify the handshake from the terminal:

opencode mcp list
opencode mcp debug nanobanana

A working setup should show nanobanana connected. If it fails, check three things in order: the environment variable is exported, oauth is explicitly false, and the authorization header includes the Bearer prefix.

Inspect the available tools directly

You can also ask the MCP endpoint for its current tool list with a JSON-RPC request. The document provides this request shape:

curl -X POST https://nanobanana.mcp.acedata.cloud/mcp   -H 'Authorization: Bearer <token>'   -H 'Accept: application/json'   -H 'Content-Type: application/json'   --data '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'

This is a useful debugging step because model and tool schemas can change over time. Instead of hard-coding expectations in your workflow, inspect the current server response when something feels off.

A practical workflow

Once connected, keep the prompt concrete. For example, in OpenCode you might write:

Change this model image to wear this clothing image, keeping the face and pose unchanged.

Or for product work:

Put this product image into this scene image, keeping the lighting consistent.

The benefit is not only image editing; it is reducing context switching. You can prepare docs, inspect assets, call the MCP tool, and paste the resulting image URL back into your project notes or README from the same terminal session.

Closing notes

NanoBanana MCP is a good fit when you need reference-based image edits rather than a one-off generated picture. Start with a project-level opencode.json, confirm opencode mcp list shows the server as connected, and then move the config global only if you want it available everywhere.

Read the full source document here: OpenCode 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