Nanobanana MCP Server

Lean MCP server for Google's Nano Banana (Gemini) image models. Returns file paths, not base64.

Local serverstdio

What is the Nanobanana MCP server?

Lean MCP server for Google's Nano Banana (Gemini) image models. Returns file paths, not base64. Exposed over MCP by the nanobanana mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

A lean MCP server for Google's Nano Banana (Gemini) image models. It generates and edits images from any MCP client (Claude Code, Claude Desktop, Cursor) and hands back file paths instead of base64, so your agent's context stays small.

Adding it to your client

The server ships on npm as @nanobanana/mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

Its toolset

Everything the assistant can do here goes through one of these:

  • generate_image — The generate_image tool exposed by this server
  • edit_image — The edit_image tool exposed by this server
  • list_models — Takes no params. Lists the image model ids your API key can use. Handy when a pinned model id stops working, which is how earlier Nano Banana servers

Configuration

You will need 2 environment variables: GEMINI_API_KEY, GOOGLE_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the nanobanana mcp server does with a few real requests.

When to reach for it

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Nanobanana's toolset — generate_image, edit_image, list_models — is a fair guide to whether it matches your workflow. It is maintained by getjoystick; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Available tools

ToolWhat it does
generate_imageThe generate_image tool exposed by this server.
edit_imageThe edit_image tool exposed by this server.
list_modelsTakes no params. Lists the image model ids your API key can use. Handy when a pinned model id stops working, which is how earlier Nano Banana servers broke.

How to install the Nanobanana MCP server

{
  "mcpServers": {
    "nanobanana": {
      "command": "npx",
      "args": ["-y", "@nanobanana/mcp"],
      "env": {
        "GEMINI_API_KEY": "your-value",
        "GOOGLE_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
GEMINI_API_KEYCredential the server authenticates with.Yes
GOOGLE_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Nanobanana to generate image.
  • Use Nanobanana to edit image.
  • Use Nanobanana to list models.

Frequently asked questions

It connects Nanobanana to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (generate_image, edit_image, list_models) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Nanobanana directly.