Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NEXOS_API_KEY | Yes | Your Nexos.ai API key for authentication |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tasks | {
"list": {},
"cancel": {},
"requests": {
"tools": {
"call": {}
},
"prompts": {
"get": {}
},
"resources": {
"read": {}
}
}
} |
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_image | Generate a single image from a text prompt. Args: prompt: Text description of the image to generate. model: Model to use (imagen-4, imagen-4-fast, imagen-4-ultra, flux-1.1-pro, gpt-image-1). size: Image size (256x256, 512x512, 1024x1024, 1792x1024, 1024x1792). quality: Image quality (standard, hd). style: Image style (vivid, natural). Returns: Dictionary with success status, file path, and metadata. |
| start_image_batch | Start generating multiple images and return the first one. This tool starts generating multiple images in the background. It blocks until the first image is ready, then returns it along with a session ID for retrieving the remaining images. Args: prompt: Text description of the image to generate. count: Number of images to generate (2-10). model: Model to use for generation. size: Image size. quality: Image quality (standard, hd). style: Image style (vivid, natural). Returns: Dictionary with session_id, first_image_path, and pending_count. |
| get_next_image | Get the next available image from a batch generation session. This tool retrieves the next image from an ongoing batch generation. If an image is already available, it returns immediately. Otherwise, it blocks until an image becomes available or timeout. Args: session_id: Session ID from start_image_batch. timeout: Maximum time to wait for an image (seconds, 1-300). Returns: Dictionary with file_path, has_more flag, and pending_count. |
| get_batch_status | Get the current status of a batch generation session. Args: session_id: Session ID from start_image_batch. Returns: Dictionary with session status, completed/pending counts, and errors. |
| list_models | List all available image generation models with their descriptions. Returns a comprehensive list of all available models including:
Use this tool to discover which models are available and choose the best one for your image generation needs. Returns: Dictionary with models list and default model information. |
| get_model_details | Get detailed information about a specific image generation model. Args: model_id: The model identifier (e.g., 'imagen-4', 'imagen-4-fast', 'dall-e-3'). Returns: Dictionary with complete model details including capabilities, rate limits, use cases, strengths, and weaknesses. Returns an error if the model is not found. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| models_catalog | Get the complete catalog of available image generation models. Returns a comprehensive list of all available models with their capabilities, rate limits, use cases, strengths, and weaknesses. |