Nano BananaSAFE
A Nano Banana MCP server, which you can integrate to cursor/claude code and any mcp client
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
🤖 This project was entirely generated by [Claude Code](https://claude.ai/code) - an AI coding assistant that can create complete, production-ready applications from scratch.
A Model Context Protocol (MCP) server that provides AI image generation and editing capabilities using Google's Gemini 2.5 Flash Image API. Generate stunning images, edit existing ones, and iterate on your creations with simple text prompts.
✨ Features
- 🎨 Generate Images: Create new images from text descriptions
- ✏️ Edit Images: Modify existing images with text prompts
- 🔄 Iterative Editing: Continue editing the last generated/edited image
- 🖼️ Multiple Reference Images: Use reference images for style transfer and guidance
- 🌍 Cross-Platform: Smart file paths for Windows, macOS, and Linux
- 🔧 Easy Setup: Simple configuration with API key
- 📁 Auto File Management: Automatic image saving with organized naming
🔑 Setup
- Get your Gemini API key:
- Visit Google AI Studio
- Create a new API key
- Copy it for configuration
- Configure the MCP server:
See configuration examples for your specific client below (Claude Code, Cursor, or other MCP clients).
💻 Usage with Claude Code
Configuration:
Add this to your Claude Code MCP settings:
Option A: With environment variable (Recommended - Most Secure)
{
"mcpServers": {
"nano-banana": {
"command": "npx",
"args": ["nano-banana-mcp"],
"env": {
"GEMINI_API_KEY": "your-gemini-api-key-here"
}
}
}
}Option B: Without environment variable
{
"mcpServers": {
"nano-banana": {
"command": "npx",
"args": ["nano-banana-mcp"]
}123e1959c78cOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add nano-banana-mcp --env GEMINI_API_KEY=${GEMINI_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"nano-banana-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"GEMINI_API_KEY": "${GEMINI_API_KEY}"
}
}
}
}Exposed tools (6)
5 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
configure_gemini_token | read | Configure your Gemini API token for nano-banana image generation |
continue_editing | read | Continue editing the LAST image that was generated or edited in this session, optionally using additional reference images. Use this for iterative improvements, modifications, or changes to the most recent image. This automatically uses the previous image without needing a file path. |
edit_image | write | Edit a SPECIFIC existing image file, optionally using additional reference images. Use this when you have the exact file path of an image to modify. |
generate_image | read | Generate a NEW image from text prompt. Use this ONLY when creating a completely new image, not when modifying an existing one. |
get_configuration_status | read | Check if Gemini API token is configured |
get_last_image_info | read | Get information about the last generated/edited image in this session (file path, size, etc.). Use this to check what image is currently available for continue_editing. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@google/genai, @modelcontextprotocol/sdk, dotenv, zod, @types/node, @typescript-eslint/eslint-plugin, @typescript-eslint/parser, eslint
Gates applied: no_behavioural_pass.
123e1959c78cfull audit observations/trust-audit/mcp-server/conechoai__nano-banana-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | 123e1959c78c | SAFE | B | 89 | first audit |
Questions
What is the Nano Banana MCP server?
A Nano Banana MCP server, which you can integrate to cursor/claude code and any mcp client
What tools does Nano Banana expose?
6 in total: 5 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Nano Banana safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Nano Banana need?
It reads GEMINI_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Nano Banana run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as nano-banana-mcp at 1.0.3.
How current is this page?
The grade is for one exact copy of the source (123e1959c78c), read on 2026-10-06. The repository is watched and re-audited when it changes.