nanobanana-mcp-server — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Monitor this implementation for changes in adoption, MCP interface, maintenance and permission boundary.

Reviewed Oct 10, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Generate and save images with Google Gemini or Vertex AI

What we know

AI image generation MCP server powered by Google Gemini, with smart model selection and 4K output Generate and save images with Google Gemini or Vertex AI.

Maintenance / activity evidence

GitHub REST pushed_at 2026-10-07T00:47:33Z

Tracking evidence observed Oct 10, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: medium.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Scoped by connected account, local OS, and configuration; verify exact permissions before installation. Reported action classes: write output image files. Complete write authority is not verified.
Gemini API key or Google Cloud Vertex AI identity
Image prompts transmitted to model provider; generated files written locally

Image generation uses billable third-party API; outputs saved to local path; Vertex authentication is an alternative.

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

400 repository stars

Stars observed Oct 9, 2026.

Repository total for zhongweili/nanobanana-mcp-server.

All limitations / Review context

Has nanobanana-mcp-server changed its specific MCP integration, install method or privilege scope, and does it justify shortlist promotion?

High-impact permissions explicitly documented; no known blocker to an accurately caveated public Radar listing in limited first-party review.

Image generation uses billable third-party API; outputs saved to local path; Vertex authentication is an alternative.
Scoped by connected account, local OS, and configuration; verify exact permissions before installation.
Gemini API key or Google Cloud Vertex AI identity
Image prompts transmitted to model provider; generated files written locally
Reviewed write actions: write output image files
Complete write authority is not verified.
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
No exhaustive advisory or runtime review performed; never infer installation safety.
Write actions/tool inventory not confirmed against exact tool documentation; listed action classes remain illustrative or context-dependent. Empty inventory does not establish read-only.
Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation.
Repository pushed_at explicitly observed

Original activity observations

GitHub REST pushed_at 2026-10-07T00:47:33Z

Technical identity

github.com/zhongweili/nanobanana-mcp-server

Exact implementation source: https://github.com/zhongweili/nanobanana-mcp-server ↗
Reviewed resource type: MCP Server
Repository identity: zhongweili/nanobanana-mcp-server

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 10, 2026 · Latest source observation Oct 10, 2026

GitHub repository ↗
zhongweili/nanobanana-mcp-server
Recorded repository material and project history.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
Publisher-documented install or connect path; prerequisites and any extra host configuration remain required.
publisher install or stdio launch · Publisher instructions
uvx nanobanana-mcp-server@latest
Configure / authenticate
MCP100 setup guide
Set GEMINI_API_KEY, or configure Vertex AI ADC as an alternative. Register `uvx nanobanana-mcp-server@latest` as stdio in your chosen MCP host.
Check connection
Suggested check
Use host tool discovery and test a non-billed metadata operation if available; image generation may incur Google charges.
Remove / uninstall / revoke
MCP100 setup guide
If registered in Claude Code under the name `nanobanana`, remove the client entry with `claude mcp remove nanobanana`. For other MCP hosts remove the matching server/connector in that host’s MCP settings. Remove a globally installed software package separately if applicable; this does not delete data or revoke a service credential.
Client removal, software uninstall, persistent-data deletion and credential revocation are separate actions.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove nanobanana

Official Documentation & Sources

What it does

AI image generation MCP server powered by Google Gemini, with smart model selection and 4K output Generate and save images with Google Gemini or Vertex AI.

Capability: Design & Creative
Resource type: MCP Server
Best fit: Generate and save images with Google Gemini or Vertex AI

Representative uses

Generate images from text prompts
Choose between Gemini API and Vertex AI authentication
Save generated images to a configured output directory
Generate and save images with Google Gemini or Vertex AI

Limitations

Image generation uses billable third-party API; outputs saved to local path; Vertex authentication is an alternative.
Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation.
Repository pushed_at explicitly observed

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Gemini API key or Google Cloud Vertex AI identity
Permissions: Scoped by connected account, local OS, and configuration; verify exact permissions before installation.
Data handling: Image prompts transmitted to model provider; generated files written locally
Cost: may incur external API or infrastructure charges; unverified
Risk and cautions: Image generation uses billable third-party API; outputs saved to local path; Vertex authentication is an alternative.

Access scope and cautions

Write actions: Not verified write output image files
Risk level: moderate
Security notes: Image generation uses billable third-party API; outputs saved to local path; Vertex authentication is an alternative.

The reviewed evidence does not establish the complete write authority of this MCP. Consult the unresolved evidence before granting write access.

FAQ

Based on reviewed evidence as of 2026-10-09. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Generate images from text prompts; Choose between Gemini API and Vertex AI authentication; Save generated images to a configured output directory; Generate and save images with Google Gemini or Vertex AI.

What setup and authentication are documented?

Recorded installation/entrypoint step: uvx nanobanana-mcp-server@latest. Recorded environment-variable notes: GEMINI_API_KEY. No configuration values are supplied here. Prerequisites: MCP-compatible client. Client notes: Command provided only where first-party command or package existence is established; verify the client configuration against upstream documentation. Google Vertex alternative uses NANOBANANA_AUTH_METHOD=vertex_ai and GCP_PROJECT_ID / GCP_REGION; GEMINI_API_KEY is for API-key mode. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Gemini API key or Google Cloud Vertex AI identity

Can it modify data or perform write operations?

Not verified. The available evidence does not establish the complete write authority. The partial inventory lists: write output image files. Recorded permission context: Scoped by connected account, local OS, and configuration; verify exact permissions before installation.

What data-handling boundary should I consider?

Image prompts transmitted to model provider; generated files written locally

What limitations and risks should I check before use?

Image generation uses billable third-party API; outputs saved to local path; Vertex authentication is an alternative. Setup and runtime permissions are implementation- and account-specific; follow linked upstream documentation. Repository pushed_at explicitly observed. No exhaustive advisory or runtime review performed; never infer installation safety.