Nano Banana
NPM · @MINDSTONE/MCP-SERVER-NANO-BANANA
Nano Banana MCP server — Google Gemini image generation and editing via Model Context Protocol
Available components
Last scanned (18 hours ago)
Scores higher than 82% of npm servers
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 30 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency87
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to mindstone/mcp-servers). View diagnostics → Pass
- License check failed: the license (FSL-1.1-MIT) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 1 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability60
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 963 tokens (~321/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Nov 26 +14
- Malware scan: unverified → pass ▲ security
- Stability: pass → 0.93 functional
- 2 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Schema quality: 290 → 321 ▼ functional
- Package version: 0.4.1 → 0.5.0 functional
- 28 Oct 26 +1
- Stability: 0.97 → pass security
- 27 Oct 26 −1
- Stability: pass → 0.97 functional
- 24 Oct 26 −5
- CVE-2023-54404 affects this package: high ▼ security
- Known CVEs: pass → fail ▼ security
- 21 Oct 26 +1
- Stability: 0.97 → pass security
- 20 Oct 26 −1
- Stability: pass → 0.97 functional
- 17 Oct 26 +3
- Stability: 0.83 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Analysed npm/@mindstone/mcp-server-nano-banana@0.5.0
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | mindstone/mcp-servers |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/mindstone/mcp-servers/.github/workflows/release.yml@refs/heads/main |
| Rekor log index | 3647543503 |
| Predicate type | SLSA build provenance https://slsa.dev/provenance/v1 |
| Subject digest | sha512:d890aadd6dc0e305da5da3020657e140376d8220f01ced1528731a31a8bfb9d64ed5b8c2c1709268dff8d31406f594a307d22305e61ee436186953914 |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 30 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
configure_nano_banana_api_key Configure NanoBanana API Key ~113
Host-managed setup only. The user adds the Gemini API key in Settings → Connectors in the app. Do not ask for or accept the key in chat. WHERE TO GET A KEY: Go to https://aistudio.google.com/api-keys → Create new API key → Copy the key. FREE TIER: Generous free usage for Gemini API. Supports image generation and editing.
| Name | Type | Req | Description |
|---|---|---|---|
| api_key | string | yes | Gemini API key from https://aistudio.google.com/api-keys |
No output schema declared.
No examples provided.
nano_banana_edit Edit Image (Nano Banana) ~474
Edit one or more existing images using Google Gemini's image editing capabilities. Use this when the user wants to modify, edit, or transform an existing image using AI, or combine elements from several images into one. Provide up to 14 source images — workspace file paths or https:// URLs — and edit instructions. The edited image will appear inline in the conversation. Examples of edit prompts: - "Remove the background and make it transparent" - "Change the color of the car to red" - "Add a sunset sky in the background" - "Make this photo look like a watercolor painting" - "Combine these images: put the product from the first image on the table from the second"
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | Aspect ratio for the edited image |
| image_size | string | – | Output resolution: "1K" (default, ~1024px), "2K", or "4K". Only sent to the Gemini 3 image models and gemini-nano-banana-2.1 — gemini-2.5-flash-image always produces ~1K. |
| model | string | – | Model to use: "gemini-3.1-flash-image" (Nano Banana 2, default — pro-quality at flash speed), "gemini-3-pro-image" (Nano Banana Pro — highest quality), "gemini-nano-banana-2.1" (Nano Banana 2.1 — new… |
| prompt | string | yes | Instructions for how to edit the image(s) |
| save_path | string | – | Optional file path to save the edited image. IMPORTANT: Must be inside the workspace directory so the image can be displayed inline. |
| source_image_path | string | – | Image to edit: a workspace file path (supports ~ for home directory) or an https:// URL. Single-image shorthand for source_image_paths — provide one or the other (or both). |
| source_image_paths | array | – | Up to 14 reference images to edit or combine (multi-image composition/fusion). Each entry follows the same rules as source_image_path. |
No output schema declared.
No examples provided.
nano_banana_generate Generate Image (Nano Banana) ~376
Generate images from text descriptions using Google Gemini's image generation capabilities. Use this when the user asks you to create, generate, draw, or design an image, illustration, or visual content using Gemini/Google AI. The generated image will appear inline in the conversation. You can also save it to disk by providing save_path. Tips for good prompts: - Be specific about style, colors, composition, and mood - Mention artistic styles if relevant (e.g., "watercolor", "minimalist", "photorealistic") - Include details about lighting, perspective, and background
| Name | Type | Req | Description |
|---|---|---|---|
| aspect_ratio | string | – | Aspect ratio for the generated image (default: 1:1) |
| image_size | string | – | Output resolution: "1K" (default, ~1024px), "2K", or "4K". Only sent to the Gemini 3 image models and gemini-nano-banana-2.1 — gemini-2.5-flash-image always produces ~1K. |
| model | string | – | Model to use: "gemini-3.1-flash-image" (Nano Banana 2, default — pro-quality at flash speed), "gemini-3-pro-image" (Nano Banana Pro — highest quality), "gemini-nano-banana-2.1" (Nano Banana 2.1 — new… |
| prompt | string | yes | Text description of the image to generate |
| save_path | string | – | Optional file path to save the image. IMPORTANT: Must be inside the workspace directory so the image can be displayed inline. |
No output schema declared.
No examples provided.
How do I install the Nano Banana MCP server?
Nano Banana runs locally as an npm package, launched with npx -y @mindstone/mcp-server-nano-banana. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @mindstone/mcp-server-nano-banana
claude mcp add mindstone-mcp-server-nano-banana -- npx -y @mindstone/mcp-server-nano-banana
What is the Nano Banana MCP server?
Nano Banana is an MCP server listed in the public MCP registry as io.github.mindstone/mcp-server-nano-banana. Nano Banana MCP server, Google Gemini image generation and editing via Model Context Protocol. This page covers its npm package (@mindstone/mcp-server-nano-banana).
Is the Nano Banana MCP server safe to use?
Nano Banana scores 84 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 4 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Nano Banana MCP server expose?
Nano Banana exposes 3 tools: configure_nano_banana_api_key, nano_banana_generate, nano_banana_edit. Their descriptions and schemas cost roughly 963 tokens of context every time the server is loaded.
Is the Nano Banana MCP server still maintained?
Nano Banana is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Nano Banana MCP server under?
Nano Banana declares the FSL-1.1-MIT licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.