Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LOG_LEVELNoLogging level: error, warn, info, debug.info
CACHE_ENABLEDNoEnable caching of results.true
MAX_IMAGE_SIZENoMaximum image size in bytes (default 10MB).10485760
SEGMIND_API_KEYYesYour Segmind API key, required for authentication.
FILE_OUTPUT_LOCATIONNoDirectory to save generated files. Defaults to system temp directory.

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
{}
logging
{}
prompts
{}
resources
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
generate_imageB

Generate images from text prompts using various AI models. Returns base64-encoded image data with MIME type information.

list_modelsB

List available AI models by category

get_model_infoA

Get detailed information about a specific model

transform_imageA

Transform existing images using AI with various control methods. Accepts file paths directly (e.g. C:\photo.jpg), URLs, or base64. File paths are automatically processed without displaying the base64 string.

generate_videoA

Generate videos from text prompts or animate static images

enhance_imageC

Enhance images with upscaling, restoration, background removal, and more. Accepts file paths directly (e.g. C:\photo.jpg), URLs, or base64. File paths are automatically processed without displaying the base64 string.

generate_audioA

Generate speech audio from text using TTS models

generate_musicC

Generate music from text descriptions

estimate_costB

Estimate the credit cost and time for image/video generation operations

check_creditsA

Check remaining API credits

prepare_imageA

RECOMMENDED: Prepare a local image file for use with other tools. Returns a short ID instead of the full base64 string, avoiding display slowdowns. Always use this instead of read_local_image for image transformation tasks.

read_local_imageA

Read a local image file and convert it to base64. WARNING: Returns the full base64 string which can be very large and slow to display. Use prepare_image instead for better performance.

Prompts

Interactive templates invoked by user choice

NameDescription
art_stylesGenerate images in specific art styles

Resources

Contextual data attached and managed by the client

NameDescription
All Available ModelsList all available Segmind models
TEXT2IMG ModelsList models in the text2img category
IMG2IMG ModelsList models in the img2img category
TEXT2VIDEO ModelsList models in the text2video category
IMG2VIDEO ModelsList models in the img2video category
TEXT2AUDIO ModelsList models in the text2audio category
TEXT2MUSIC ModelsList models in the text2music category
ENHANCEMENT ModelsList models in the enhancement category
API CreditsCheck remaining API credits

TDQS

A3.7/5.0

Scored across 12 tools

Disambiguation4/5

Most tools are clearly separated by modality and action: generate_image, transform_image, enhance_image, generate_video, generate_audio, and generate_music all have distinct purposes. The only real overlap is prepare_image versus read_local_image, though the descriptions explicitly differentiate the recommended workflow from the base64-returning alternative.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: generate_*, list_*, get_*, transform_*, enhance_*, estimate_*, check_*, prepare_*, and read_*. The verbs are descriptive and predictable across the entire set.

Tool Count5/5

Twelve tools is well-scoped for a multimodal generation server. The count covers image, video, audio, and music generation, model discovery, image utilities, cost estimation, and credit checking without unnecessary bloat.

Completeness5/5

The tool surface provides a complete workflow for the domain: model discovery, generation across multiple modalities, image transformation and enhancement, local image preparation, and account/cost management. There are no obvious dead ends or missing core operations for the stated purpose.

Maintenance

ActivityInactive
ResponsivenessNo issues