Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HF_TOKENNoOptional Hugging Face token for model downloads
COMFYUI_HOSTYesThe URL of the ComfyUI host, e.g. http://<gpu-host>:8188
LLAMASWAP_HOSTNoOptional URL for the llama-swap router, e.g. http://<gpu-host>:8089, used for GPU-yield handshake
SPARK_SSH_ALIASYesSSH alias from ~/.ssh/config for the GPU host
CIVITAI_API_TOKENNoOptional Civitai API token for gated downloads
SPARK_COMFYUI_ROOTYesPath to the ComfyUI installation on the GPU host
SPARK_COMFYUI_PYTHONYesPath to the Python executable in the ComfyUI virtual environment

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/bernardogv/comfyui-mcp'

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