Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
IMAGE_MODELNoModel name as configured in LiteLLM.minimax-h3-image
IMAGE_TIMEOUTNoHTTP timeout in seconds for image generation/editing (H3 can be slow).600
PROMPT_TIMEOUTNoChat timeout in seconds for prompt expansion (expansion models think for a while).1200
IMAGE_HTTP_PORTNoLocalhost port of the built-in image host used for chat-renderable markdown links; 0 = random port, -1 = disable.18090
LITELLM_API_KEYNoBearer token for the LiteLLM proxy, if the proxy needs one.
IMAGE_OUTPUT_DIRNoWhere generated PNGs are saved. Defaults to <script dir>/generated, or %TMP%\image-mcp\generated when the script runs from a temp dir (e.g. uv run <URL>).
LITELLM_BASE_URLYesBase URL of the LiteLLM proxy, e.g. https://litellm.example.com (add /v1 yourself only if you want). Required.
PROMPT_LLM_MODELNoChat model on the same proxy used for prompt expansion. Required for expand_prompt, and must be vision-capable if image_paths are passed.
PROMPT_VLM_MODELNoOptional separate vision model for edit-mode prompt expansion; defaults to PROMPT_LLM_MODEL.
IMAGE_PREVIEW_MAXNoMax side (px) of the inline preview the agent sees; 0 = inline full-res. Full-res files are always saved to disk.1024

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