Nanobanana (nano-banana) MCP Server
nanobanana-mcp-server
PyPI
v0.4.5
Published by nano-banana — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
A production-ready MCP server for AI-powered image generation using Gemini 3.1 Flash Image (Nano Banana 2, default), Gemini 3 Pro Image, and Gemini 2.5 Flash Image with intelligent model selection
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 4 = 96. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −3 | capability blast radius (moderate) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 2
low Shell/command execution in packaging/dev tooling (scripts/build.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/build.py:18`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run(cmd, check=True, capture_output=capture_output, text=True) if result.stdo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/build.py
low Shell/command execution in packaging/dev tooling (scripts/upload.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`scripts/upload.py:20`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: try: result = subprocess.run(cmd, check=True, capture_output=capture_output, text=True) if result.stdo
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server scripts/upload.py
Tools 3
Each tool and what it can reach — statically extracted from the published source.
upload_filenetwork egressmaintenanceno sensitive capabilityshow_output_statsno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (3 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.4.5 latest |
A 96/100 | 2 | 1.13.0 | 2026-08-25 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan nanobanana-mcp-server --online --registry pypiOther implementations of Nanobanana 7
Independent packages implementing the same tool, scanned with the same engine. Compare all 8 side by side →
MCP server for creating and editing images using Google's Gemini 2.5 Flash Image model (nanobanana)
MCP server for Gemini 3.1 Flash with vision, chat, and image generation capabilities
Lean MCP server for Google's Nano Banana (Gemini) image models. Generates and edits images, returns file paths.
MCP server for Google Gemini image generation (Nano Banana)
MCP server for Google Nano Banana image generation (Gemini)
MCP server for Nano Banana image generation (OpenRouter by default, configurable provider)
More in Design & Media
Turn designs into shipped parts: quote 3D printing, CNC, and decals, then check out.
Aleph's official SiliconFlow media-generation MCP server (image / video / TTS)
MCP server for image generation using Google Gemini AI
Ambience AI MCP Server - Generate images, videos, and audio through Model Context Protocol
MCP server exposing every endpoint of the AstroWay Calculation API as tools — natal, synastry, transits, Vedic dashas, Tarot, Numerology, Human Design, AI horoscopes — for Claude Desktop, Cursor and any MCP-compatible AI agent.
Audio-guide and trip-planning tools for 1,100+ cities from Audiala. Free, no API key.