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 embedding server, otherwise leave empty for hosted (OpenRouter/OrcaRouter)
OPENROUTER_API_KEYNoAPI key for OpenRouter hosted embeddings
ORCAROUTER_API_KEYNoAPI key for OrcaRouter hosted embeddings
LOCAL_EMBEDDING_MODELNoModel name for the local embedding server (e.g., intfloat/multilingual-e5-large)
EMBEDDING_PROMPT_STYLENoPrompt style expected by the embedding model: 'gemini', 'e5', or 'raw'
LOCAL_EMBEDDING_BASE_URLNoBase URL of the local OpenAI-compatible embedding server (e.g., http://localhost:8080/v1)
LOCAL_EMBEDDING_DIMENSIONNoOutput dimension of the local embedding model (e.g., 1024)
OPENROUTER_EMBEDDING_MODELNoModel ID for OpenRouter embeddings (default: google/gemini-embedding-001)
ORCAROUTER_EMBEDDING_MODELNoModel ID for OrcaRouter embeddings (default: google/gemini-embedding-001)
OPENROUTER_EMBEDDING_DIMENSIONNoOutput dimension for the OpenRouter embedding model (default: 3072)
ORCAROUTER_EMBEDDING_DIMENSIONNoOutput dimension for the OrcaRouter embedding model (default: 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