Image Gen MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_API_KEY | No | Alternative API key (low priority). | |
| IMAGE_GEN_MODEL | Yes | The model to use for image generation. | |
| OPENAI_BASE_URL | No | Alternative base URL (low priority). | |
| IMAGE_GEN_API_KEY | Yes | Your API key for the image generation provider. | |
| IMAGE_GEN_BASE_URL | No | Base URL for the provider API. | |
| IMAGE_GEN_ENV_FILE | No | Path to a strict env file (KEY=value format). | |
| IMAGE_GEN_PROVIDER | No | Provider to use (default 'openai-images'). | openai-images |
| IMAGE_GEN_OUTPUT_DIR | No | Output directory for generated images (default '~/Pictures/Image Gen'). | ~/Pictures/Image Gen |
| IMAGE_GEN_TIMEOUT_MS | No | Timeout in milliseconds for API requests. | |
| IMAGE_GEN_RESPONSES_MODEL | No | Model for Responses protocol (if using openai-responses). | |
| IMAGE_GEN_ALLOW_PRIVATE_URLS | No | Allow private URLs for image results (set to 'true' to allow). | 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_imageC | Generate or edit one image using the configured provider, save it locally, and return image content. |
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 1 tool
With only one tool, there is no possibility of confusion between tools.
A single tool name follows a consistent verb_noun pattern, no inconsistencies to evaluate.
One tool for both generation and editing is too thin; typical servers would have separate tools for different operations or at least more granular endpoints.
The tool conflates generation and editing into one, missing separate operations for style listing, parameter tuning, or model selection, leaving significant gaps.