Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PLUME_EMBEDDERNoThe embedder to use: auto, hash, vertex, gemini. auto: Vertex key, else Gemini key, else hash.auto
PLUME_MCP_DEBUGNoLog each MCP request's method (initialize: client, protocol, MCP Apps declared; ui:// reads; tool names). No arguments, results or tokens.false
PLUME_MODEL_LLMNoThe generation model.gemini-4-argon
PLUME_VERTEX_AUTHNoVertex auth mode: key (PLUME_VERTEX_API_KEY / PLUME_VERTEX_KEY_FILE), adc (Application Default Credentials), or auto (key if set, else ADC with a project).auto
PLUME_DATABASE_URLNoThe database URL.postgresql+psycopg://plume:plume@127.0.0.1:18432/plume
PLUME_MCP_APP_HTMLNoThe MCP App bundle (model view) served as ui://plume/model-view.the packaged file
PLUME_GEMINI_API_KEYNoGemini API key (never logged).
PLUME_VERTEX_API_KEYNoVertex AI API key (never logged).
PLUME_VERTEX_PROJECTNoVertex project. With a project, generation calls the model at PLUME_VERTEX_LOCATION; without one, the location-less express URL.
PLUME_VERTEX_KEY_FILENoThe Vertex key as a file (read when used, never logged).
PLUME_VERTEX_LOCATIONNoVertex location for generation calls when PLUME_VERTEX_PROJECT is set.global
PLUME_MCP_CORS_ORIGINSNoJSON list of browser origins allowed to call the MCP endpoints (browser-based MCP clients). Off by default.[]
PLUME_MODEL_MAX_ROUNDSNoThe generation model's repair rounds.3
PLUME_MAINTAINER_TOKENSNoJSON list of maintainer tokens, each at least 16 characters. Empty list disables the maintainer API (503).[]
PLUME_MCP_ALLOWED_HOSTSNoHost headers the MCP server accepts.loopback
PLUME_EVIDENCE_BUDGET_CHARSNoAPI evidence server generation sends the model, shared fairly by the APIs (~4 characters per prompt token).200000
PLUME_VERTEX_EMBED_LOCATIONNoThe embedding model's location on the project path (whenever PLUME_VERTEX_PROJECT is set, key or ADC).global

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