Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoHost or interface to bind to. Defaults to 127.0.0.1 locally; deployment sets 0.0.0.0.
PORTNoPort to listen on. Defaults to 8080 locally; deployment sets 8000.
ALLOWED_EMAILSNoOptional comma-separated allowlist to narrow the proxy's allowlist for image generation.
GEMINI_API_KEYYesYour Google AI Studio API key for the Gemini image model.
IMAGE_MCP_MODELNoDefault model to use, e.g. gemini-2.5-flash-image.
IMAGE_MCP_TOKENNoStatic bearer token for local token auth. Required when IMAGE_MCP_TRUST_PROXY_HEADERS is not set.
IMAGE_MCP_GCS_BUCKETNoCloud Storage bucket used for storing images larger than IMAGE_MCP_INLINE_MAX_BYTES. Required for 2K/4K image sizes.
IMAGE_MCP_MAX_PROMPTNoMaximum number of characters allowed in an image generation prompt.
IMAGE_MCP_RATE_PER_HOURNoMaximum number of image generation requests allowed per hour per instance.
IMAGE_MCP_ALLOWED_MODELSNoComma-separated list of models that callers may select.
IMAGE_MCP_MAX_CONCURRENCYNoMaximum number of concurrent image generation requests per instance.
IMAGE_MCP_INLINE_MAX_BYTESNoMaximum image size in bytes returned inline before the image is uploaded to Cloud Storage. Default is 1500000 (1.5 MB).
IMAGE_MCP_TRUST_PROXY_HEADERSNoSet to 1 when running behind mcp-oauth-proxy. The server reads user identity from X-Auth-* headers instead of requiring its own token. Never enable on a routable port.

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ramzpat/image-gen-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server