Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_API_KEYYes**Required.** Provider API key.
GATEWAY_PORTNoBind port.8000
LLM_BASE_URLNoOpenAI-compatible base URL.https://api.openai.com/v1
LLM_MODEL_IDNoModel id or alias.gpt-6-sol
MCP_TRANSPORTNostdio, http, or sse.stdio
MCP_SERVER_URLNoCommand (stdio) or URL (http/sse). (empty by default)
GATEWAY_API_KEYNoWhen set, /v1/* requires Authorization: Bearer. (empty by default)
MCP_ALLOWED_TOOLSNoComma-separated allowlist; empty = read-only defaults. (empty by default)
MCP_MAX_TOOL_ROUNDSNoCap on model → tool → model rounds.5
LLM_REASONING_EFFORTNonone/low/medium/high/xhigh/max. (empty by default)
MCP_REQUIRE_APPROVALNoRequire approval for risky tools.true

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