Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HF_ENDPOINTNoMirror used for the one-time embedding model download from Hugging Face.https://huggingface.co
SEMBLE_MODEL_NAMENoAlternative Model2Vec embedding model, specified as a local path or a Hugging Face repository.minishlab/potion-code-16M-v2
SEMBLE_CLONE_TIMEOUTNoSeconds allowed for cloning an `https://` repository.60
SEMBLE_INDEX_WORKERSNoNumber of worker processes used to chunk a repository during the first index build; `0` chunks in-process.4
SEMBLE_CACHE_LOCATIONNoDirectory where Semble stores its disk index caches. Move it to share caches with the `/semble` CLI reports.
SEMBLE_MAX_FILE_BYTESNoFiles above this size in bytes are skipped during indexing.1000000
SEMBLE_MCP_IDLE_TIMEOUTNoSeconds an idle repository index stays in the in-memory cache; `0` means never evict.0

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