Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
N_THREADSNoNumber of CPU threads4
MODEL_PATHYesPath to your GGUF model file
CONTEXT_SIZENoMaximum context window size2048
N_GPU_LAYERSNoGPU layers (use -1 for all, 0 for CPU only)0
SESSION_AUTO_TRIMNoAutomatically trim history when limits exceededtrue
STREAMING_ENABLEDNoEnable streaming responses (tokens sent incrementally)false
SESSION_HISTORY_DIRNoDirectory for storing conversation historyhistory
SESSION_MAX_MESSAGESNoMaximum messages per session (older messages trimmed)40
STREAMING_CHUNK_SIZENoApproximate chunk size for streaming (characters)50
SESSION_MAX_FILE_BYTESNoMaximum size per session file (bytes)2097152

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/Marcel-MSC/local-llm-mcp-tool'

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