Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RAG_N_CTXNoContext size for the RAG model2048
RAG_TOP_KNoNumber of top results to retrieve in RAG5
MCP_DATA_DIRNoDirectory for MCP data storage.data
RAG_N_THREADSNoNumber of threads for RAG computation4
MCP_DB_TIMEOUTNoTimeout in seconds for database operations30
RAG_CHUNK_SIZENoChunk size for RAG document splitting512
REMOTE_LOG_DIRNoDirectory for storing remote operation logs./logs/remote
RAG_N_GPU_LAYERSNoNumber of GPU layers for model acceleration0
RAG_CHUNK_OVERLAPNoOverlap between chunks in RAG64
EMBEDDING_MODEL_PATHNoPath to the embedding model file for hybrid RAGresources/models/embedding_model.gguf

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/MSelcukAkbas/versatile-mcp'

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