Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FAST_MODELNoModel for short triage/classification
AGENT_MODELNoOverride the model name
COMFYUI_HOSTNoWhere ComfyUI runs127.0.0.1
COMFYUI_PORTNoComfyUI port8188
LLM_PROVIDERNoLLM provider: anthropic, openai, gemini, ollamaanthropic
VISION_MODELNoModel for vision tools
GEMINI_API_KEYNoYour Google Gemini API key (required if using Gemini provider)
OPENAI_API_KEYNoYour OpenAI API key (required if using OpenAI provider)
OLLAMA_BASE_URLNoOllama server URLhttp://localhost:11434/v1
THINKING_BUDGETNoExtended-thinking budget per agent turn (Anthropic Claude 4.x+ only)4000
COMFYUI_DATABASENoYour ComfyUI folder~/ComfyUI
ANTHROPIC_API_KEYNoYour Anthropic API key (required if using Anthropic provider)
VISION_THINKING_BUDGETNoExtended-thinking budget for vision-tool calls2000

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/JosephOIbrahim/Comfy-Cozy'

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