Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
EMBEDDING_PROVIDERNoSet to 'local' to use a local OpenAI-compatible embedding server; otherwise OpenRouter is used. Optional — semantic search is disabled if not configured.
OPENROUTER_API_KEYNoOpenRouter API key (only for hosted embeddings). Get it from https://openrouter.ai/keys.
LOCAL_EMBEDDING_MODELNoThe local embedding model name, e.g. intfloat/multilingual-e5-large.
EMBEDDING_PROMPT_STYLENoThe prefix style expected by the model: 'gemini', 'e5', or 'raw'.
LOCAL_EMBEDDING_BASE_URLNoThe OpenAI-compatible URL of the local embedding server, e.g. http://localhost:8080/v1.
LOCAL_EMBEDDING_DIMENSIONNoThe output dimension of the local embedding model (must match), e.g. 1024.
OPENROUTER_EMBEDDING_MODELNoOpenRouter embedding model id. Default is google/gemini-embedding-001.
OPENROUTER_EMBEDDING_DIMENSIONNoThe output dimension of the OpenRouter embedding model. Default is 3072.

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