Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
JEV_BACKENDNoSelect Jev backend: auto (TypeSafe key first), typesafe, or gateway.auto
TYPESAFE_API_KEYNoAPI key for TypeSafe's Jev model.
AI_GATEWAY_API_KEYNoAPI key for Vercel AI Gateway's Jev model.
CLAUDE_PROJECT_DIRNoSet by Claude Code; the MCP server uses this as the project root.
CONTEXT_PACKER_ROLESNoSet to 0 to turn off role labels.1
CONTEXT_PACKER_LAYA_URLNoLocal Laya endpoint. Loopback HTTP only.http://127.0.0.1:8770/api/predict
CONTEXT_PACKER_PROVIDERNoDefault provider when none is given to pack_context.keywords
CONTEXT_PACKER_EXTENSIONSNoExtension allowlist, such as 'kt,kts'. Defaults to all supported extensions.
CONTEXT_PACKER_HOOK_LIMITNoFiles the hook adds, 1 to 20.8
CONTEXT_PACKER_LAYA_MODELNoLaya model ID.english
CONTEXT_PACKER_COMPARE_TOPNoSet to 0 to turn off the top-ten comparison.1
CONTEXT_PACKER_TOKEN_BUDGETNoReported Jev input tokens per process before new packs are refused. Checked between packs, so it isn't a hard cap.20000000
CONTEXT_PACKER_HOOK_DEADLINENoSeconds before the hook gives up. For CPU Laya, use 180 and a hook timeout of at least 190.25
CONTEXT_PACKER_HOOK_PROVIDERNoProvider the hook uses.keywords

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