Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_MODELNoLLM model name. Defaults depend on the selected provider, e.g. gpt-4o-mini for OpenAI or llama3.1 for Ollama.
LLM_PROVIDERNoLLM provider. Supported values: fake, openai, ollama.fake
OPENAI_API_KEYNoOpenAI API key. Optional unless using OpenAI as the LLM or embedding provider.
EMBEDDING_MODELNoEmbedding model name. Defaults depend on the selected provider, e.g. text-embedding-3-small for OpenAI or nomic-embed-text for Ollama.
OLLAMA_BASE_URLNoURL of the Ollama server.http://localhost:11434
OPENAI_BASE_URLNoBase URL for an OpenAI-compatible endpoint.
ASSISTANT_DB_PATHNoPath to the SQLite database used by the MCP server. The README example uses an absolute path to assistant.sqlite3.
EMBEDDING_PROVIDERNoEmbedding provider. Supported values: hash, openai, ollama.hash

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