Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MARS_HOSTNoAdditional Ollama host
LUNAR_HOSTNoLight inference Ollama host
GALAXY_HOSTNoGPU inference Ollama host
OLLAMA_HOSTNoLocal Ollama host127.0.0.1
EXPLORA_HOSTNoHeavy compute Ollama host
GROQ_API_KEYNoAPI key for Groq
GITHUB_API_KEYNoAPI key for GitHub Models
MISTRAL_API_KEYNoAPI key for Mistral
CEREBRAS_API_KEYNoAPI key for Cerebras
GOOGLE_AI_API_KEYNoAPI key for Google AI
OPENROUTER_API_KEYNoAPI key for OpenRouter
TOKEN_SCOUT_MAX_COSTNoMaximum cost per 1K tokens (0 for free only, 0.001 default)0.001

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/jackccrawford/token-scout'

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