Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
KB_TOP_KNoOverride for the number of top results (default: 5)
KB_RAW_DIRNoOverride for the raw documents directory (default: private)
KB_LLM_MODELNoOverride for the LLM model name (default: gemma4:latest)
KB_CHUNK_SIZENoOverride for the chunk size (default: 1200)
KB_EMBED_MODELNoOverride for the embedding model name (default: nomic-embed-text)
KB_OLLAMA_HOSTNoOverride for the Ollama host URL (default: http://localhost:11434)
KB_STORAGE_DIRNoOverride for the storage directory (default: .kb/storage)
KB_SOURCES_FILENoOverride for the sources file path (default: .kb/sources.txt)
KB_CHUNK_OVERLAPNoOverride for the chunk overlap (default: 150)

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/jcode-works/jcode-mimir'

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