Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
COMFY_RPC_URLNoOverrides the public repository default https://evmrpc.0g.ai. Must use HTTPS; HTTP is allowed only for localhost, 127.0.0.1, or [::1].https://evmrpc.0g.ai
COMFY_SESSIONNoOptional session for owner-authorized comfy_jobs results. A 24-hour session from the comfy CLI, passed as an environment variable. Optional for all public tools and required for an owner-authorized comfy_jobs result. Honoured on stdio only; the --http listener never forwards it.
COMFY_MCP_PORTNoPort for the streamable-http transport. Overridden by --port, then defaults to 8931.8931
COMFY_ENGINE_ORIGINNoBase URL of the Comfy engine REST API. Defaults to https://warmth.comfy.fun.https://warmth.comfy.fun
COMFY_MCP_TIMEOUT_MSNoBounds each upstream request. Default is 5000; valid range is 100 to 60000.5000
COMFY_INFINITY_DEPLOYMENTNoNames the deployment the market tools read, as chainId:manager:splitter. Defaults to comfy.fun's; a malformed value falls back to it.
COMFY_INDEXER_GRAPHQL_HTTPNoURL of the Comfy indexer GraphQL endpoint. Defaults to https://indexer.comfy.fun/v1/graphql.https://indexer.comfy.fun/v1/graphql

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