Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
H3_MODELNoOverride for the diffusion model filename (default minimax_h3_fl2va_pruned_int8_convrot.safetensors).
COMFYUI_URLNoURL of the ComfyUI server. MCP restricts COMFYUI_URL to local HTTP addresses, expected to be accessed via an SSH tunnel (e.g. http://127.0.0.1:8188).http://127.0.0.1:8188
H3_AUDIO_VAENoOverride for the audio VAE filename (default minimax_h3_audio_vae_fp32.safetensors).
H3_VIDEO_VAENoOverride for the video VAE filename (default minimax_h3_video_vae_fp16.safetensors).
H3_OUTPUT_DIRNoLocal directory where completed videos are downloaded (e.g. /absolute/path/h3-cloud-mcp/outputs).
H3_TEXT_ENCODERNoOverride for the text encoder filename (default qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors).

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