NanoBanana Pro 2

io.github.u2n4Published by GitHub account u2n4v1.1.2Updated Oct 24, 2026

4K AI image generation via NanoBanana Pro 2: Pro + Flash models, Google Search grounding

VerifiedSTDIODesktop onlyMedia & Design AI & ML

Server details

Identifier: io.github.u2n4/nanobanana-imagen-mcp
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account u2n4 for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.u2n4%2Fnanobanana-imagen-mcp.svg)](https://sourceweft.com/mcp/io.github.u2n4%2Fnanobanana-imagen-mcp?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Local MCP server that lets an assistant generate and edit AI images with NanoBanana Pro 2 (Pro and Flash models) at up to 4K resolution.

What you can do: Generate images from text prompts with model, aspect ratio, resolution, negative prompt, thinking level, grounding and batch options, and edit images using uploaded reference images for consistent multi-angle results. Upload reference images for editing or conditioning. Review statistics on generated images, including count, total size and file details. Run maintenance to clear caches, remove temporary files and optimize storage.
When to use it: Useful when you want an assistant to create or edit images on demand, from quick Flash iterations to high-quality 4K Pro renders, including real-world subjects via Google Search grounding.
Requirements: Runs locally as a Python package (pip or uvx) on desktop. Requires a Gemini API key in the GEMINI_API_KEY environment variable. Optionally set IMAGE_OUTPUT_DIR for output location and NANOBANANA_DB_PATH for the SQLite metadata database; network access is needed for generation.

Before you install

The Gemini API key is a credential and is passed in plain configuration. Generation sends prompts and any reference images to Google's Gemini service. Images and a SQLite metadata database are written to disk by default; maintenance can delete caches and temporary files, and setting NANOBANANA_DB_PATH to :memory: discards image history on restart.

Installation

In SourceWeft

Open NanoBanana Pro 2 in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

NanoBanana MCP Server

MCP server for AI image generation using NanoBanana Pro 2. Supports Pro (maximum quality) and Flash (fast generation) models with default 4K resolution.

Inspired by the nano-banana naming convention used across the MCP community. This is an independent implementation.

Quick Install

Claude Desktop (claude_desktop_config.json):

json

{  "mcpServers": {    "nanobanana": {      "command": "uvx",      "args": ["nanobanana-imagen-mcp"],      "env": {        "GEMINI_API_KEY": "your_key_here"      }    }  }}

{  "mcpServers": {    "nanobanana": {      "command": "uvx",      "args": ["nanobanana-imagen-mcp"],      "env": {        "GEMINI_API_KEY": "your_key_here"      }    }  }}

Variable	Description	Default
`GEMINI_API_KEY`	Gemini API key — required for all generation	--
`IMAGE_OUTPUT_DIR`	Directory where generated images are saved	`~/nanobanana-images`
`NANOBANANA_DB_PATH`	SQLite database path for image metadata	`~/nanobanana-images/images.db`

What It Does

Generates AI images using NanoBanana Pro 2 models. Supports text-to-image generation, image editing with reference images, file uploads, and server maintenance. Produces high-quality images at up to 4K resolution.

Tools (4)

Tool	Description
`generate_image`	Generate images using NanoBanana Pro 2. Supports model selection (Pro/Flash), aspect ratio, resolution (up to 4K), negative prompts, thinking level, grounding, reference images, and batch generation.
`upload_file`	Upload a reference image for use in image editing or conditioning.
`show_output_stats`	Display statistics about generated images — count, total size, file details.
`maintenance`	Server maintenance and cleanup — clear caches, remove temporary files, optimize storage.

Models

Configuration

Storage

Generated image metadata is tracked in a SQLite database.

Opt out of persistent storage by setting NANOBANANA_DB_PATH=:memory:. This uses an in-memory database that is discarded when the server exits — useful for ephemeral or read-only environments. Trade-off: image history is lost on restart; the show_output_stats tool will show an empty database each session.

The database and output directories are created lazily on first image generation — starting the server with no GEMINI_API_KEY set (e.g. nanobanana-imagen-mcp --help) does not create any files or directories.

Claude Desktop Configuration

From pip (recommended)

json

{  "mcpServers": {    "nanobanana": {      "command": "uvx",      "args": ["nanobanana-imagen-mcp"],      "env": {        "GEMINI_API_KEY": "your_key_here"      }    }  }}

{  "mcpServers": {    "nanobanana": {      "command": "uvx",      "args": ["nanobanana-imagen-mcp"],      "env": {        "GEMINI_API_KEY": "your_key_here"      }    }  }}

From this repository

json

{  "mcpServers": {    "nanobanana": {      "command": "python",      "args": ["-m", "servers.nanobanana.nanobanana_mcp_server.server"],      "env": {        "GEMINI_API_KEY": "your_key_here"      },      "cwd": "path/to/gemini-media-mcp"    }  }}

{  "mcpServers": {    "nanobanana": {      "command": "python",      "args": ["-m", "servers.nanobanana.nanobanana_mcp_server.server"],      "env": {        "GEMINI_API_KEY": "your_key_here"      },      "cwd": "path/to/gemini-media-mcp"    }  }}

Features

Default 4K resolution for maximum detail
Pro model for complex, photorealistic scenes
Flash model for fast iterations and simple subjects
Reference image support for consistent multi-angle shots
Negative prompt support for quality control
Thinking level control for complex multi-element scenes
Google Search grounding for real-world subjects

License

MIT

Credits

Inspired by the nano-banana naming convention used across the MCP community. This is an independent implementation.

Source: servers/nanobanana/README.md at commit 1b8fc5a

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v1.1.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts

Model	Engine	Best For
Pro	Gemini 3 Pro Image	Maximum quality, complex scenes, photorealism
Flash	Gemini 3.1 Flash Image	Fast generation, simple scenes, quick iterations