An MCP server for AI-powered image generation, editing, and video generation using Google Gemini and Veo models
Detailed security scan evidence is not public for this MCP yet. Public identity, registry metadata, and independently observed protocol inventory remain available.
Installation and connection instructions are shown only when supported by retained package, repository, or endpoint evidence.
Version 1.2.1 declares 1 executable entrypoint.
npm install --save-exact @seungmanchoi/nano-banana-mcp@1.2.1npx -y -p @seungmanchoi/nano-banana-mcp@1.2.1 @seungmanchoi/nano-banana-mcp{
"mcpServers": {
"@seungmanchoi/nano-banana-mcp": {
"command": "npx",
"args": [
"-y",
"-p",
"@seungmanchoi/nano-banana-mcp@1.2.1",
"@seungmanchoi/nano-banana-mcp"
]
}
}
}| Canonical slug | gemini-nano-banana-mcp-d1723738 | Deployment | Local Only |
|---|---|---|---|
| Canonical package | npm:@seungmanchoi/nano-banana-mcp | Repository | seungmanchoi/nano-banana-mcp |
| First published | — | Latest release | — |
| Last security verification | — | Classification confidence | 90% |
| Publication | Draft | Official distribution | Not verified |
| Channel | Identifier | Current version | Versions | Source |
|---|---|---|---|---|
| npm | @seungmanchoi/nano-banana-mcp | 1.2.1 | 1 | Repository |
| Package | Version | Published / observed | Inventory | Security scan |
|---|---|---|---|---|
| npm@seungmanchoi/nano-banana-mcp | 1.2.1Current | Sep 5, 2026 | 9 toolsSucceeded · 0 resources · 0 prompts | Evidence restricted |
Independently scan the exact version your agents use, receive alerts when its risk changes, and investigate every finding with retained version evidence.
No public current-version evidence is available yet.
| Tool | Category | Annotations | Risk |
|---|---|---|---|
configure_api_keySet or update the Gemini API key for image generation. The key is stored locally and persists across sessions.Input schema{
"type": "object",
"properties": {
"apiKey": {
"type": "string",
"description": "Your Google Gemini API key (get one at https://aistudio.google.com/apikey)"
}
},
"required": [
"apiKey"
]
} | — | — | |
configure_modelSet the default Gemini model for image generation and editing. Persists across sessions. Recommended: gemini-2.0-flash-preview-image-generation (default, free tier). Also available: imagen-3.0-generate-002 (best quality, requires billing), imagen-3.0-fast-generate-001 (fast, requires billing).Input schema{
"type": "object",
"properties": {
"model": {
"type": "string",
"description": "Gemini model ID to use (e.g. gemini-2.0-flash-preview-image-generation)"
}
},
"required": [
"model"
]
} | — | — | |
continue_editingContinue editing the last generated or edited image. Automatically uses the most recent image from the session.Input schema{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Instructions for the next edit"
},
"referenceImages": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional reference images for guidance"
},
"model": {
"type": "string",
"description": "Optional model override for this request"
}
},
"required": [
"prompt"
]
} | — | — | |
edit_imageEdit an existing image based on text instructions. Provide the file path of the image to modify.Input schema{
"type": "object",
"properties": {
"imagePath": {
"type": "string",
"description": "Absolute file path to the image to edit"
},
"prompt": {
"type": "string",
"description": "Instructions for how to edit the image"
},
"referenceImages": {
"type": "array",
"items": {
"type": "string"
},
"description": "Optional array of file paths to reference images for style or content guidance"
},
"model": {
"type": "string",
"description": "Optional model override for this request (e.g. gemini-2.0-flash-preview-image-generation)"
}
},
"required": [
"imagePath",
"prompt"
]
} | — | — | |
generate_imageGenerate a new image from a text description using Gemini AI. Returns the generated image and saves it to disk.Input schema{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Detailed description of the image to generate"
},
"model": {
"type": "string",
"description": "Optional model override for this request (e.g. gemini-2.0-flash-preview-image-generation)"
}
},
"required": [
"prompt"
]
} | — | — | |
generate_videoGenerate a video from a text prompt using Gemini Veo. Supports text-to-video, image-to-video (first frame), and first+last frame interpolation. Video generation takes 1-6 minutes. Available models: veo-3.1-generate-preview (latest), veo-3-generate-preview, veo-2-generate-preview.Input schema{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "Detailed description of the video to generate. Include subject, action, style, camera movement, and atmosphere."
},
"model": {
"type": "string",
"description": "Veo model to use. Options: veo-3.1-generate-preview (default, latest), veo-3-generate-preview, veo-2-generate-preview."
},
"imagePath": {
"type": "string",
"description": "Optional: Absolute file path to an image to use as the first frame (image-to-video generation)."
},
"lastFramePath": {
"type": "string",
"description": "Optional: Absolute file path to an image to use as the last frame (first+last frame interpolation). Requires imagePath to be set."
},
"aspectRatio": {
"type": "string",
"description": "Aspect ratio of the video. Options: \"16:9\" (default, landscape), \"9:16\" (portrait)."
},
"resolution": {
"type": "string",
"description": "Video resolution. Options: \"720p\" (default), \"1080p\", \"4k\"."
},
"durationSeconds": {
"type": "number",
"description": "Video duration in seconds. Options: 4, 6, 8 (default varies by model)."
},
"numberOfVideos": {
"type": "number",
"description": "Number of video variants to generate (default: 1)."
},
"negativePrompt": {
"type": "string",
"description": "Optional: Elements to avoid in the generated video."
}
},
"required": [
"prompt"
]
} | — | — | |
get_statusCheck the current configuration status, active model, and last image/video information.Input schema{
"type": "object",
"properties": {}
} | — | — | |
list_historyList recently generated and edited images with their prompts and timestamps.Input schema{
"type": "object",
"properties": {
"count": {
"type": "number",
"description": "Number of recent images to show (default: 10, max: 50)"
}
}
} | — | — | |
list_video_historyList recently generated videos with their prompts, models, and timestamps.Input schema{
"type": "object",
"properties": {
"count": {
"type": "number",
"description": "Number of recent videos to show (default: 10, max: 50)"
}
}
} | — | — |
| Endpoint | Transport | Authentication | Health | Observed |
|---|---|---|---|---|
| No verified remote endpoint is linked. | ||||
Install the selected package version with: npm install --save-exact @seungmanchoi/nano-banana-mcp@1.2.1
Gemini Nano Banana MCP Server exposed 9 tools during independent protocol observation, including configure_api_key, configure_model, continue_editing, edit_image, generate_image, generate_video, get_status, list_history, and others.
The selected current version does not yet have completed public verification. Unknown does not mean clean or vulnerable.
These internal links are derived from strong identity fields such as the implementation name, package, repository, vendor, and listing name—not generic description prose.
Association is based on retained identity fields; it does not by itself prove first-party publication.
Curated product and capability guides containing this catalog record.