Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DEBUGNoEnable debug logging (set to any value)
GEMINI_MODELSNoAdditional models for Gemini (JSON object of model->description).
CODEX_CONFIG_PATHNoPath to Codex config file.
VIBE_ACTIVE_MODELNoOverride active model for Mistral Vibe.
LLM_GATEWAY_CONFIGNoPath to gateway TOML config (default: ~/.llm-cli-gateway/config.toml)
CODEX_DEFAULT_MODELNoExplicit default model for Codex.
GEMINI_HISTORY_ROOTNoPath to Gemini history root directory.
LLM_GATEWAY_JOBS_DBNoDeprecated legacy env var. Use config.toml instead.
LLM_GATEWAY_LOGS_DBNoDeprecated: override persistence path. Use config.toml instead.
CLAUDE_DEFAULT_MODELNoExplicit default model for Claude.
CLAUDE_SETTINGS_PATHNoPath to Claude settings file.
GEMINI_DEFAULT_MODELNoExplicit default model for Gemini.
GEMINI_MODEL_ALIASESNoAliases for Gemini models.
GEMINI_SETTINGS_PATHNoPath to Gemini settings file.
GROK_CODE_XAI_API_KEYNoAPI key for Grok CLI (alternative to OAuth login).
LLM_GATEWAY_AUTH_TOKENNoBearer token for HTTP transport authentication.
LLM_GATEWAY_MODEL_ALIASESNoGlobal model aliases for all CLIs.
CLAUDE_SETTINGS_LOCAL_PATHNoPath to Claude local settings file.
LLM_GATEWAY_APPROVAL_POLICYNoDefault approval policy (strict, balanced, permissive)
LLM_GATEWAY_DEDUP_WINDOW_MSNoOverride dedupWindowMs for async job deduplication.
LLM_GATEWAY_JOB_RETENTION_DAYSNoOverride retentionDays for job persistence.
LLM_GATEWAY_ACKNOWLEDGE_EPHEMERALNoSet to 1/true/yes to acknowledge ephemeral backend for async tools.
LLM_GATEWAY_DISABLE_MODEL_DISCOVERYNoSet to 1 to disable local model-history discovery.

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/verivus-oss/llm-cli-gateway'

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