Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
EMBEDDINGSNoEmbedding backend: 'local' (default, paraphrase-multilingual-MiniLM-L12-v2), 'voyage', or 'none' (keyword only).local
MCP_SECRETNoHigh-entropy secret (24+ characters) for remote mode. Required when running in remote (HTTP) mode.
MEMORY_REPOYesYour private GitHub repository for memory, e.g. 'you/my-memory'.
MEMORY_ROOTNoRoot directory for memory files.memory
GITHUB_TOKENYesGitHub fine-grained token with Contents: Read and write permission for your memory repo.
MEMORY_BRANCHNoGit branch for memory.main
PROMPT_RECALLNoSet to '0' to turn off the per-prompt hook.1
VOYAGE_API_KEYNoAPI key for Voyage, needed when EMBEDDINGS=voyage.
ANTHROPIC_API_KEYNoAPI key for Anthropic, only needed for 'maintain rewrite='.
CORE_BUDGET_TOKENSNoHard cap for pinned memory in tokens.400
GITHIPPO_HOOK_PROFILENoHook profile, e.g. 'minimal' to reduce hooks.
GITHIPPO_DISABLED_HOOKSNoComma-separated list of hooks to disable, e.g. 'prompt,steer'.

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

Maintenance

ActivityMaintained
ResponsivenessResponsive