Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
rootNoRoot folder the MCP server may read and write inside, passed as --root. Defaults to the folder the server starts in; the server refuses to start when it is a drive or file-system root or your home folder.
MASKBOLT_MODEL_DIRNoDirectory for the downloaded model cache. Default: %LOCALAPPDATA%\maskbolt\models on Windows, $XDG_CACHE_HOME/maskbolt/models or ~/.cache/maskbolt/models elsewhere.
MASKBOLT_DECODE_THREADSNoNumber of threads used to decode prompts (up to 16).
MASKBOLT_ENCODE_THREADSNoNumber of tiles encoded in parallel (default 4; each holds about 1.2 GB at peak; 1 gives about 3.3 GB peak).4

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