MCP Banana Image
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Google AI or Cliproxy API key | |
| GEMINI_BASE_URL | No | Custom API endpoint (e.g., Cliproxy) | https://generativelanguage.googleapis.com |
| IMAGE_OUTPUT_DIR | No | Output directory for generated images | ./output |
| SKIP_PROMPT_ENHANCEMENT | No | Disable automatic prompt optimization | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Generate images from simple text prompts with automatic prompt enhancement for professional results. Use this when:
NOT for:
Example: "Create a hero image for a coffee shop website" |
| edit_imageA | Edit existing images using natural language instructions. Use this when:
NOT for:
Example: "Remove the background from this product photo" |
| convert_imageA | Convert images between formats without AI processing. Use this when:
NOT for:
Example: "Convert photo.png to WebP format with 80% quality" |
| resize_imageA | Resize images to specific dimensions without AI processing. Use this when:
NOT for:
Example: "resize_image inputPath='./photo.jpg' width=800 height=600 fit='cover'" |
| generate_logoA | Generate professional logos with text support and multiple style options for branding. Use this when:
NOT for:
Chain with: If user requests specific pixel dimensions for the logo, chain with resize_image after generation. Example: "generate_logo businessName='TechStart' tagline='Innovation Made Simple' style='modern'" |
| generate_iconA | Generate icons, avatars, and stickers - small visual assets optimized for clarity at small sizes. Use this when:
NOT for:
Chain with: If user requests specific pixel dimensions for icons (e.g., 512x512, 192x192), chain with resize_image after generation. Example: "generate_icon description='shopping cart' purpose='icon' style='outlined'" |
| generate_productA | Generate professional e-commerce product photography that drives purchases with automatic style optimization. Use this when:
NOT for:
Chain with: If user requests specific pixel dimensions for marketplace requirements, chain with resize_image after generation. Example: "generate_product productDescription='handmade leather wallet' style='premium'" |
| generate_social_mediaA | Generate platform-optimized social media content with correct dimensions and engagement-focused styling. Use this when:
NOT for:
Chain with: If user requests specific pixel dimensions beyond platform defaults, chain with resize_image after generation. Example: "generate_social_media content='summer sale announcement' platform='instagram-post'" |
| generate_ugcA | Generate authentic user-generated content style images that look natural, relatable, and not AI-generated. Use this when:
NOT for:
Chain with: If user requests specific pixel dimensions, chain with resize_image after generation. Example: "generate_ugc description='person enjoying morning coffee' scenario='lifestyle' setting='home'" |
| remove_backgroundA | Remove backgrounds from images to create transparent PNGs for product shots, portraits, and design assets. Use this when:
NOT for:
Example: "remove_background imagePath='/path/to/product.jpg'" |
| analyze_imageA | Analyze images using AI vision to generate descriptions, alt-text, tags, or detailed semantic analysis. Use this when:
NOT for:
Example: "analyze_image imagePath='/path/to/photo.jpg' analysisType='description'" |
| blend_imagesA | Blend multiple images together using AI-powered composition with various blend modes (seamless, collage, double-exposure, overlay). Use this when:
NOT for:
Example: "blend_images imagePaths=['./bg.jpg', './subject.png'] instruction='Place subject on background' blendMode='seamless'" |
| generate_infographicA | Generate AI-powered infographic images from content descriptions with customizable styles, layouts, and branding. Use this when:
NOT for:
Chain with: If user requests specific pixel dimensions, chain with resize_image after generation. Example: "generate_infographic content='5 steps to improve productivity: 1. Set goals 2. Prioritize tasks 3. Eliminate distractions 4. Take breaks 5. Review progress' style='corporate' layout='vertical'" |
| generate_character_setA | Generate consistent character images across multiple poses and expressions for character series, mascots, or visual narratives. Use this when:
NOT for:
Chain with: If user requests specific pixel dimensions for character images, chain with resize_image after generation. Example: "generate_character_set characterDescription='friendly robot mascot with blue eyes' poses=['front', 'waving', 'thinking'] style='cartoon'" |
| style_transferA | Apply artistic style from a reference image to new or existing content while preserving the content structure. Use this when:
NOT for:
Chain with: If user requests specific pixel dimensions for styled images, chain with resize_image after generation. Example: "style_transfer referenceStyleImage='./van-gogh.jpg' contentDescription='mountain landscape at sunset' styleStrength=0.8" |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 15 tools
Every tool carries explicit 'Use this when / NOT for / use X instead' guidance, so the eight generate_* variants are clearly separated by domain (logo, icon, product, social, UGC, infographic, character set). The only residual overlap is conceptual: generate_product vs generate_ugc vs generate_social_media can all produce marketing imagery, and style_transfer vs blend_images both combine references, though descriptions steer correctly.
Nearly all names follow a snake_case verb_noun pattern (generate_image, edit_image, convert_image, resize_image, remove_background, analyze_image, blend_images). The single deviation is 'style_transfer', which inverts to noun_verb, a minor inconsistency in an otherwise predictable scheme.
Fifteen tools sit at the top of the well-scoped range for an image media server. Each has a distinct modality or operation, and the specialized generators justify their separation through differing parameters (platform, poses, brand text, layout) rather than being duplicates.
The surface covers the full lifecycle: generation (general + specialized), editing, style transfer, blending, background removal, analysis/OCR, format conversion, and resizing, with documented chaining to resize_image. Minor gaps remain: no crop/rotate/upscale, no text or watermark overlay, and no metadata/inspection tool for existing files.