Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
COMFYUI_URLNoWhich ComfyUI to talk to.http://127.0.0.1:8188
AI_STATION_HOMENoWhere the station gate lives. If set and it holds no gate, the answer is no gate — this server does not quietly look somewhere else.$HOME/.ai-station
IRSOFKA_COMFY_GATENo`off` disables the gate by operator order; every affected answer then says `BYPASSED`.
COMFYUI_OUTPUT_ROOTNoWhere ComfyUI writes its images, for `view_image`.auto-detected
COMFY_MCP_ASSET_TTL_HOURSNoHow long a fetched asset stays in the local registry.24
IRSOFKA_COMFY_ALLOW_NETWORKNoRegisters `view_image`, the one tool that can fetch a caller-supplied URL. Unset by default (refuse).

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