Schema | imagen

imagen

Describes the environment variables required to run the server.

Name	Required	Description	Default
`IMAGEN_HOST`	No	Bind address for imagen serve.	127.0.0.1
`IMAGEN_PORT`	No	Port for imagen serve.	4747
`GEMINI_API_KEY`	No	Enables the gemini provider. Get a key at Google AI Studio.
`GOOGLE_API_KEY`	No	Alternative environment variable that enables the gemini provider.
`OPENAI_API_KEY`	No	Enables the openai provider.
`IMAGEN_ENV_FILE`	No	Path to an environment file to load.
`OPENAI_BASE_URL`	No	Optional OpenAI-compatible base URL.
`IMAGEN_OUTPUT_DIR`	No	Default output folder. Tools can override it per call with output_dir.	~/.imagen/images
`IMAGEN_PUBLIC_URL`	No	Base URL advertised in the A2A agent card and image URLs.	http://HOST:PORT
`IMAGEN_DEFAULT_MODEL`	No	Model used when a request omits one, e.g. openai/gpt-image-2. Defaults to the first configured model.
`AZURE_FOUNDRY_API_KEY`	No	Key for the Azure AI Foundry resource.
`AZURE_FOUNDRY_ENDPOINT`	No	Azure AI Foundry resource endpoint, e.g. https://my-resource.services.ai.azure.com.
`AZURE_FOUNDRY_API_VERSION`	No	Azure AI Foundry API version query parameter.	preview
`AZURE_FOUNDRY_DEPLOYMENTS`	No	Comma-separated Azure deployment names, e.g. gpt-image-1.5,FLUX.2-pro,FLUX-1.1-pro. Append :bfl or :openai to force a route.
`GEMINI_USE_GENERATE_CONTENT`	No	Set to 1 to use the classic generateContent API instead of the Interactions API.	off

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.

Server capabilities have not been inspected yet.

Functions exposed to the LLM to take actions

Name	Description
No tools

Interactive templates invoked by user choice

Name	Description
No prompts

Contextual data attached and managed by the client

Name	Description
No resources

This server cannot be deployed

ActivityMaintained

ResponsivenessUnresponsive