Nano Banana 2 Lite with Codex

title: Nano Banana 2 Lite with Codex published: true series: MCP date: 2026-07-04 02:14:56 UTC tags: python,openaicodex,nanobanana,mcps canonical_url: https://xbill999.medium.com/nano-banana-2-lite-with-codex-8a58f159dd51

This article covers the MCP setup and configuration for using Google Nano Banana 2 Lite and underlying Gemini LLM with Codex CLI to enhance and extend image operations over the MCP protocol.

What is Google Nano Banana 2 Lite?

Nano Banana 2 Lite (officially known as the Gemini 3.1 Flash-Lite Image model) is Google’s fastest and most cost-efficient AI image generation and editing model. It is built specifically for enterprises and developers who need to generate high-quality images quickly and affordably at a large scale. [1, 2, 3]

Key Features

Lightning-Fast Latency: Capable of generating high-quality images in about 4 seconds. [1, 2]
Cost-Efficient Pricing: Priced at approximately $0.034 per 1,000 images in Google AI Studio, undercutting standard models and previous versions. [1]
Real-World Grounding: Integrates with Google Web and Image Search to produce highly accurate visuals based on real-world information, such as live weather data and exact global locations. [1, 2]
Pro-Level Editing: Allows for nuanced image-editing capabilities, aspect ratio control, and text rendering/translation directly onto images. [1, 2]
Character Consistency: Retains the fidelity of subjects across multiple generations and scenarios, making it highly effective for storyboarding and marketing campaigns. [1, 2]

More details are here:

Start building with Nano Banana 2 Lite and Gemini Omni Flash

and here:

Gemini 3.1 Flash-Lite Image (Nano Banana 2 Lite) | Gemini Enterprise Agent Platform | Google Cloud Documentation

Haven’t You Done this One Before?

What is old is new.

This article extends a previous article covering using Antigravity CLI with MCP servers. The original article is here:

Nano Banana 2 Lite with MCP, and Antigravity CLI

The same structured approach is used to enable Python MCP servers on Claude Code CLI.

This seems Pretty Basic- why even Bother?!

When configuring a new environment and new tools — the key to a successful deployment is to validate the basic building blocks for the approach. Python MCP servers allow CLI tools like Codex to be dynamically extended with a clear approach to enable minimal MCP tools. Before attempting more complicated MCP tools — a set of basic MCP commands with the simplest MCP protocol (stdio) is used to verify the functionality.

What is MCP?

Unless you have been living off grid without Internet- MCP is the new universal connector and next “Big Thing”.

More information is here:

What is Model Context Protocol (MCP)? A guide

Python MCP Documentation

The official GitHub Repo provides samples and documentation for getting started:

GitHub - modelcontextprotocol/python-sdk: The official Python SDK for Model Context Protocol servers and clients

Isn’t MCP overkill?

There are many ways to call models. Native MCP support in Codex opens up a new pathway to call the underlying Nano Bananna model.

Integrating Codex with Nano Banana 2 Flash Lite

Pairing Codex with Nano Banana 2 Lite expands the agent’s core capabilities, allowing it to act on multimodal inputs and execute complex tasks on your behalf.

So what is the Secret Sauce?

The Interactions API allows for a clean consistent call to the model.

The Interactions API is Google’s unified interface for building with Gemini AI models and autonomous agents. Rather than using multiple separate endpoints for text chat, tool use, image generation, or background agents, it provides a single, streamlined API to handle complex, stateful workflows. [1, 2, 3]

More information is here:

Interactions API | Gemini API | Google AI for Developers

and here:

Gemini Interactions API | Gemini API | Google AI for Developers

but wait — there’s more!

There is A Skill for That!

You can make the magic happen!

Interactions API: our primary interface for Gemini models and agents

npx skills add google-gemini/gemini-skills --skill gemini-interactions-api

Setup the Basic Environment

At this point you should have a working Python environment and a working Codex CLI installation. The next step is to clone the GitHub samples repository with support scripts:

cd ~
git clone https://github.com/xbill9/nb2lite-codex

Then run init.sh from the cloned directory.

The script will attempt to determine your shell environment and set the correct variables:

cd nb2lite-codex
source init.sh

If your session times out or you need to re-authenticate- you can run the set_env.sh script to reset your environment variables:

cd nb2lite
source set_env.sh

Variables like PROJECT_ID need to be setup for use in the various build scripts- so the set_env script can be used to reset the environment if you time-out.

Running the Python Code

First- switch the directory with the Python version of the MCP sample code:

make install
pip install -r requirements.txt

The project can also be linted:

xbill@penguin:~/nb2lite-codex$ make lint
ruff check .
All checks passed!
ruff format --check .
2 files already formatted
mypy .
Success: no issues found in 2 source files

Codex MCP Config

A sample MCP server file is provided:

m3:.codex xbill$ more config.toml 
  [mcp_servers.nb2lite-agent]
  command = "/opt/homebrew/bin/python3"
  args = ["/Users/xbill/nb2lite-codex/server.py"]
  enabled = true
  env_vars = ["GEMINI_API_KEY", "GOOGLE_API_KEY"]

  [mcp_servers.nb2lite-agent.tools.generate_image]
  approval_mode = "approve"

[mcp_servers.nb2lite-agent.tools.get_help]
approval_mode = "approve"

[mcp_servers.nb2lite-agent.tools.edit_image]
approval_mode = "approve"

[mcp_servers.nb2lite-agent.tools.edit_local_image]
approval_mode = "approve"

Validation with Codex CLI

The final connection test uses Codex CLI as a MCP client with the Python code providing the MCP server:

/mcp

🔌 MCP Tools

  • codex_apps
    • Auth: Bearer token
    • Tools: (none)

  • nb2lite-agent
    • Auth: Unsupported
    • Tools: edit_image, edit_local_image, generate_image, get_help

the tools are reviewed:


• nb2lite-agent exposes these MCP tools:

  - generate_image - generate a new image from a prompt.
  - edit_image - edit a previously generated image using its interaction ID.
  - edit_local_image - edit a local image file by path.
  - get_help - show server help, config, and tool details.

  Current model: gemini-3.1-flash-lite-image
  Output directory: /Users/xbill/nb2lite-codex

We have Lift Off!

Finally- the tools are now available for working with the Nano Banana2 Lite models:

› summarize the nblite mcp tools

• nb2lite-agent provides image generation and editing tools backed by Gemini.

  - generate_image: Creates a new image from a text prompt. Supports aspect ratios like 1:1,
    16:9, 9:16, 4:3, 3:4.

  - edit_image: Edits a previously generated image using its interaction_id, preserving session
    continuity.

  - edit_local_image: Edits an existing local image file from a filesystem path.
  - get_help: Returns server help, current config, and available tool details.

  Current setup:

  - Model: gemini-3.1-flash-lite-image
  - Output folder: /Users/xbill/nb2lite-codex
  - API key status: set

Enough, Already! Show me the Money!

Codex CLI was started up for a hands-on image editing session:

› call mcp tool generate_image codex banana

Not a fan of Bananas?

› use the mcp tool edit_image make the banana an apple with Saved image:
    gen_1783125858_21c75be6.jpg

    Interaction ID:

    v1_ChdZVmRJYW9pRUhlX2FqckVQcnFPTC1BOBIXWVZkSWFvaUVIZV9hanJFUHJxT0wtQTg

• I’ll use edit_image with the interaction ID so the server edits the existing banana session
  into an apple while preserving the mascot style.

• Called
  └ nb2lite-
        agent.edit_image({"previous_interaction_id":"v1_ChdZVmRJYW9pRUhlX2FqckVQcnFPTC1BOBIXWVZ
        kSWFvaUVIZV9hanJFUHJxT0wtQTg","edit_prompt":"Transform the banana mascot into a playful
        futuristic Codex apple mascot. Preserve the same centered composition, polished
        stylized 3D illustration style, clean studio lighting, expressive friendly eyes, subtle
        software-engineering circuit-like markings, and tiny terminal charm. The subject should
        clearly be a bright apple instead of a banana. No text, no
        watermark.","thinking_level":"low"})
    🟢 Image successfully saved!
    • Saved to: /Users/xbill/nb2lite-codex/edit_1783126427_6b6cef2d.jpg
    • Interaction ID: v1_ChdZVmRJYW9pRUhlX2FqckVQcnFPTC1BOBIXbWxsSWFyNjhMWnpxanJFUHVkMnJxQVU

───────────────────────────────────────────────────────────────────────────────────────────────

• Edited successfully.

  Saved image:
  edit_1783126427_6b6cef2d.jpg

  New interaction ID:

  v1_ChdZVmRJYW9pRUhlX2FqckVQcnFPTC1BOBIXbWxsSWFyNjhMWnpxanJFUHVkMnJxQVU

Not a fan of Apples?

› use the mcp tool edit local image to make [Image #1] a pineapple

• I’ll use edit_local_image on the local file and ask it to convert the apple mascot into a
  pineapple while keeping the same pose, lab setting, and 3D Codex style.

• Called
  └ nb2lite-agent.edit_local_image({"image_path":"/Users/xbill/nb2lite-codex/
        edit_1783126427_6b6cef2d.jpg","edit_prompt":"Transform the apple mascot into a playful
        futuristic Codex pineapple mascot. Preserve the same centered composition, pose,
        friendly expression, polished stylized 3D illustration quality, clean sci-fi lab
        background, studio lighting, subtle software-engineering circuit-like markings, limbs,
        tiny terminal charm, and overall mascot feel. The subject should clearly be a pineapple
        with a golden textured pineapple body and green leafy crown instead of an apple. No
        text, no watermark.","aspect_ratio":"1:1","thinking_level":"low"})
    🟢 Image successfully saved!
    • Saved to: /Users/xbill/nb2lite-codex/edit_local_1783126589_39305f53.jpg
    • Interaction ID: v1_ChdQRnBJYXNUMUFZQ2JqckVQaXZDRXlBTRIXUEZwSWFzVDFBWUNianJFUGl2Q0V5QU0

───────────────────────────────────────────────────────────────────────────────────────────────

• Edited local image successfully.

  Saved image:
  edit_local_1783126589_39305f53.jpg

  Interaction ID:

  v1_ChdQRnBJYXNUMUFZQ2JqckVQaXZDRXlBTRIXUEZwSWFzVDFBWUNianJFUGl2Q0V5QU0

One last example — the banner for this article was re-themed in steam-punk style:

› use the nblite mcp tools to retheme this as steam-punk: Saved image:
    gen_1783111489_1ac76ec9.jpg

    Interaction ID:

    v1_ChdRUjlJYW91b0NxT2dqckVQZzVhTS1RTRIXUVI5SWFvdW9DcU9nanJFUGc1YU0tUU0

• I’ll use the existing interaction ID with edit_image so the original Codex pet is rethemed
  into steampunk while keeping the same mascot identity and composition.

• Called
  └ nb2lite-
        agent.edit_image({"previous_interaction_id":"v1_ChdRUjlJYW91b0NxT2dqckVQZzVhTS1RTRIXUVI
        5SWFvdW9DcU9nanJFUGc1YU0tUU0","edit_prompt":"Retheme the existing Codex pet mascot as
        steampunk. Preserve the same main character identity, friendly expression, centered
        composition, compact companion-creature proportions, and polished stylized 3D
        illustration quality. Replace the futuristic software aesthetic with brass and copper
        mechanical details, tiny gears, rivets, leather straps, clockwork accents, warm amber
        glow, and subtle Victorian workshop atmosphere. Keep it approachable and memorable. No
        text, no watermark.","thinking_level":"low"})
    🟢 Image successfully saved!
    • Saved to: /Users/xbill/nb2lite-codex/edit_1783126855_06812b3a.jpg
    • Interaction ID: v1_ChdRUjlJYW91b0NxT2dqckVQZzVhTS1RTRIXUmx0SWFvdmFGYWl4MU1rUHNwMm53QW8

───────────────────────────────────────────────────────────────────────────────────────────────

• Rethemed successfully.

  Saved image:
  edit_1783126855_06812b3a.jpg

  Interaction ID:

  v1_ChdRUjlJYW91b0NxT2dqckVQZzVhTS1RTRIXUmx0SWFvdmFGYWl4MU1rUHNwMm53QW8

One last thought- Where are Agents?

Where are the Agents?

The Codex CLI harness itself uses agents to manage the workflow.

The additional touch point for leveraging the MCP interface is that they all are exposed as MCP tools. The MCP tools can be called directly from Agent code or used as a template for Interactions API calls embedded in an Agent.

Summary

The strategy for using MCP with Nano Banana 2 Lite and Codex CLI was validated with a incremental step by step approach.

A minimal stdio transport MCP Server was started from Python source code and validated with Codex CLI running as a MCP client in the same local environment.

This MCP Python server provided all of the management tools to interact with the model and generate high quality cyberpunk banana images.