Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_HOSTNoThe host URL for the Ollama server.http://localhost:11434
GROQ_API_KEYYesAPI key for Groq models.
DEFAULT_MODELNoThe default model to use for prompts.openai:gpt-4o-mini
GEMINI_API_KEYYesAPI key for Google Gemini models.
OPENAI_API_KEYYesAPI key for OpenAI models.
DEEPSEEK_API_KEYYesAPI key for DeepSeek models.
ANTHROPIC_API_KEYYesAPI key for Anthropic models.
DEFAULT_TEAM_MODELSNoA JSON array string representing the default list of models used by the agile team.["openai:gpt-4.1","anthropic:claude-3-7-sonnet","gemini:gemini-2.5-pro"]
DEFAULT_DECISION_MAKER_MODELNoThe default model used to make decisions in team workflows.openai:gpt-4o-mini

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/danielscholl/agile-team-mcp-server'

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