Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
OLLAMA_HOSTNoHost URL for Ollama. Required if EMBEDDING_PROVIDER is 'Ollama'; default 'http://127.0.0.1:11434'.http://127.0.0.1:11434
MILVUS_TOKENNoToken for Milvus. Required if EMBEDDING_PROVIDER is 'VoyageAI' (cloud). Optional for local.
MILVUS_ADDRESSNoAddress of the Milvus vector store. Required for both providers.
EMBEDDING_MODELNoThe embedding model name. For VoyageAI: 'voyage-4-large'; for Ollama: 'nomic-embed-text'.nomic-embed-text
VOYAGEAI_API_KEYNoAPI key for VoyageAI. Required if EMBEDDING_PROVIDER is 'VoyageAI'.
EMBEDDING_PROVIDERNoThe embedding provider. Must be 'VoyageAI' or 'Ollama'.
VOYAGEAI_RERANKER_MODELNoReranker model for VoyageAI. Optional, default 'rerank-2.5'.rerank-2.5
EMBEDDING_OUTPUT_DIMENSIONNoOutput dimension of the embedding model. Required for VoyageAI; default '1024'.1024

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

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/ham-zax/satori'

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