imagent
by 1mrnewton
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IMAGENT_MAX_N | No | Maximum number of images per call. | 4 |
| IMAGENT_MODEL | No | Default model for generate_image. | gpt-image-2.6-flare |
| OPENAI_ORG_ID | No | Optional OpenAI organization ID. | |
| OPENAI_API_KEY | Yes | Required OpenAI API key with image access. | |
| IMAGENT_QUALITY | No | Default image quality: low, medium, high, xhigh, max, or auto. | medium |
| OPENAI_BASE_URL | No | Optional base URL, e.g. for a proxy or gateway. | |
| IMAGENT_PROVIDER | No | Optional provider ID to select a registered image provider. | |
| IMAGENT_SVG_MODEL | No | Text model that writes SVG code when format is svg (OpenAI requires one). | gpt-5.4-mini |
| IMAGENT_EDIT_MODEL | No | Default model for edit_image. | gpt-image-2.6-sunburst |
| IMAGENT_OUTPUT_DIR | No | Where files go when no absolute output_path is given. Defaults to ./generated-images (or ~/Pictures/generated-images when the client starts in / or ~). | ./generated-images |
| IMAGENT_TIMEOUT_MS | No | OpenAI request timeout in milliseconds. | 300000 |
| IMAGENT_PREVIEW_SIZE | No | Longest edge of the preview returned to the model. | 512 |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessSyncing