Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OPENAI_MODELNoThe OpenAI model identifier to use with the 'openai' provider. Defaults to the provider's built-in default if not set.
OPENAI_API_KEYNoYour OpenAI API key. Required when using the 'openai' provider.
AGENT_TEAM_PROVIDERNoThe provider adapter to use: openai, openai-compatible, hermes, or mock.openai
AGENT_TEAM_ALLOWED_ROOTNoAbsolute path to the allowed root directory for project analysis. The server will only read files within this root.
OPENAI_COMPATIBLE_MODELNoModel name for the OpenAI-compatible API. Required when using the 'openai-compatible' provider.
OPENAI_COMPATIBLE_API_KEYNoAPI key for the OpenAI-compatible API. Required when using the 'openai-compatible' provider.
OPENAI_COMPATIBLE_BASE_URLNoBase URL for an OpenAI-compatible API (e.g. Ollama, vLLM, LocalAI). Required when using the 'openai-compatible' provider.

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

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_expertsA

List the expert roles available in this agent team.

ask_expertC

Ask one specialist to review a task and the readable source files in a project.

run_teamC

Run the connected PM, architecture, programming, QA and security workflow.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources