Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DO_NOT_TRACKNoSet to `1` to disable the one anonymous usage ping per day.
ENGRAM_TOOLSNoSet to `all` to load the 40 Advanced MCP tools in addition to the 19 Core tools that are loaded by default.
ENGRAM_SEARCHNoSet to `hybrid` to opt in to hybrid retrieval (FTS5 full-text plus a semantic vector layer) instead of the default keyword search. Requires installing `piia-engram[vector]`.
ENGRAM_APPROVALNoSet to `strict` to gate every write behind user review. By default, low/medium writes are auto-absorbed and only high-risk items (credentials, shell commands, MCP config, permission rules) wait for approval.
ENGRAM_NO_UPDATE_CHECKNoSet to `1` to disable the once-a-day PyPI version check performed by the `engram` command in interactive terminals (and on each `engram doctor` run).

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