Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GROK_MODELNoGrok model overridegrok-4.3
GEMINI_MODELNoGemini model overridegemini-3.5-flash
GROK_API_KEYNoxAI Grok API key (required to enable Grok)
OLLAMA_MODELNoOllama model overridellama3
OPENAI_MODELNoOpenAI model overridegpt-5.5
GEMINI_API_KEYNoGoogle Gemini API key (required to enable Gemini)
OLLAMA_ENABLEDNoSet to '1' to force-include / '0' to force-exclude the local Ollama generalunset
OPENAI_API_KEYNoOpenAI API key (required to enable OpenAI)
ANTHROPIC_MODELNoClaude model overrideclaude-fable-5
CONSENSUS_MODELNoOverride the Claude model used for the final synthesisfalls back to ANTHROPIC_MODEL
ANTHROPIC_API_KEYNoAnthropic API key (required to enable Claude) — also serves as moderator
OPENAI_COMPATIBLE_MODELNoModel identifier as the local server exposes itunset
OPENAI_COMPATIBLE_BASE_URLNoForce-enable an OpenAI-compatible local server (LM Studio, Jan, llama.cpp-server, Msty, LocalAI)unset

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/djfunboy/joint-chiefs'

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