Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AWS_REGIONNoAWS region (default: us-east-1)us-east-1
ENABLE_AWSNoEnable AWS Bedrock provider (true/false, default: false)false
AWS_PROFILENoAWS profile name (default, SSO, or named profile)
ENABLE_GEMININoEnable Google Gemini provider (true/false, default: false)false
ENABLE_OPENAINoEnable OpenAI provider (true/false, default: false)false
GEMINI_API_KEYNoGoogle Gemini API key (required if ENABLE_GEMINI is true)
OPENAI_API_KEYNoOpenAI API key (required if ENABLE_OPENAI is true)

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_modelsA

List available image generation models from all enabled providers.

Returns a formatted list of model IDs that can be used with generate_image and transform_image. Models are fetched dynamically from each provider's API.

generate_imageA

Generate an image from a text prompt using the specified model.

Args: prompt: Detailed text description of the image to generate. Be specific about subject, style, lighting, colors, composition, and mood. Example: "A fluffy orange cat sitting on a windowsill, golden hour lighting, watercolor style" model_id: Model identifier from list_models(). Examples: "amazon.nova-canvas-v1:0", "gpt-image-1.5", "models/gemini-2.5-flash-image" output_path: Absolute or relative file path where the generated image will be saved. Supports PNG, JPEG formats. Parent directories are created automatically. reference_image: Optional. Path to an existing image to use as style/content reference. The model will generate a new image influenced by this reference. width: Optional. Image width in pixels. Default: 1024. Common values: 512, 768, 1024, 1280. Note: Some models only support specific sizes. Max: 4096px. height: Optional. Image height in pixels. Default: 1024. Common values: 512, 768, 1024, 1280. Note: Some models only support specific sizes. Max: 4096px.

Returns: Success message with output path, or error description.

transform_imageA

Transform an existing image based on a text prompt.

Args: image_path: Path to the source image to transform. Supports common formats (PNG, JPEG, etc.) prompt: Text description of the desired transformation. Examples: "Make it black and white", "Add a rainbow in the sky", "Convert to watercolor painting style" model_id: Model identifier from list_models(). Examples: "amazon.nova-canvas-v1:0", "gpt-image-1.5", "models/gemini-2.5-flash-image" output_path: File path where the transformed image will be saved. Parent directories are created automatically.

Returns: Success message with output path, or error description.

prompt_guideA

Get best practices and examples for writing effective image generation prompts.

Returns guidelines for crafting detailed prompts that produce better results.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

TDQS

A4.3/5.0

Scored across 4 tools

Disambiguation4/5

The tools are mostly distinct: list_models, generate_image, transform_image, and prompt_guide each have clear roles. However, generate_image's optional reference_image overlaps with transform_image's purpose of editing an existing image, which could cause confusion when choosing between them.

Naming Consistency4/5

The first three tools follow a consistent verb_noun pattern (list_models, generate_image, transform_image). The exception is prompt_guide, which is a noun phrase rather than a verb, creating a minor deviation from the otherwise uniform naming convention.

Tool Count5/5

With 4 tools, the server is well-scoped for its stated purpose. Each tool serves an essential function in the image generation workflow, and the count is neither excessive nor too sparse.

Completeness4/5

The server covers the core image generation lifecycle: listing models, generating images, and transforming existing ones. A gap is the lack of model capability details beyond IDs, which would help agents choose the right model for a task, but this can be worked around.

Maintenance

ActivityInactive
ResponsivenessNo issues