Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_PROVIDERNoOverride for the routing LLM provider: gemini / openai / anthropic / openrouter / ollama. Defaults to the first configured provider in that order. Ollama is only used when explicitly selected.
USER_COUNTRYNoTells the router where you are (DE / TR / IR) so ambiguous questions with no place names route to your country's services. Optional; without it you can use the set_location tool.
GEMINI_API_KEYNoYour own Gemini API key for ask routing (default model gemini-3.5-flash).
MIGROS_SESSIONNoYour own session cookie for migros-mcp account write tools (cart, favorites). Passed as an env var in your MCP config; never leaves your machine.
OPENAI_API_KEYNoYour own OpenAI API key for ask routing (default model gpt-4o-mini).
ANTHROPIC_API_KEYNoYour own Anthropic API key for ask routing (default model claude-haiku-4-5).
OPENROUTER_API_KEYNoYour own OpenRouter API key for ask routing (default model nvidia/nemotron-3.5-lightning:free).
HEPSIBURADA_SESSIONNoYour own session cookie for hepsiburada-mcp account write tools (cart, favorites). Passed as an env var in your MCP config; never leaves your machine.
ALL_MCP_<PROVIDER>_MODELNoModel override for a provider, e.g. ALL_MCP_GEMINI_MODEL.

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

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