Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
API_KEYNoOptional API key for downstream (passthrough)
TIMEOUTNoRequest timeout in seconds (optional, default: 60)60
DEFAULT_MODELYesDefault model to use for completions
DOWNSTREAM_URLYesBase URL for the OpenAI-compatible downstream API
MODEL_LIST_URLNoURL to fetch available models from (optional, defaults to models.dev)models.dev

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
extensions
{
  "io.modelcontextprotocol/ui": {}
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_modelsA

List all available models from the configured providers.

Fetches models from the configured providers, with caching. Can filter by provider ID.

completeA

Send a completion request to the downstream LLM provider.

Proxies the request to the configured OpenAI-compatible downstream endpoint.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
models_listResource URI that returns the list of available models. Returns: JSON array of model objects. Example: >>> models_list() [{"id": "gpt-4", "object": "model", ...}]
config_infoResource URI that returns current gateway configuration. Returns: Configuration details including providers, model list URL, etc. Example: >>> config_info() {"model_list_url": "...", "cache_ttl": 300, "providers": [...]}
providers_listResource URI that returns the list of configured providers. Returns: JSON array of provider objects. Example: >>> providers_list() [{"id": "openai", "name": "OpenAI", "type": "openai", ...}]

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/daedalus/mcp-llm-gateway'

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