Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
DO_NOT_TRACKNoSet to `1` to turn off the anonymous daily usage ping. Network calls by default are limited to one anonymous usage ping a day.
ENGRAM_TOOLSNoSet to `all` to opt in to the 40 Advanced MCP tools in addition to the 19 Core tools loaded by default.core
ENGRAM_SEARCHNoSet to `hybrid` to enable hybrid retrieval (FTS5 full-text plus a semantic vector layer) for cross-lingual recall, e.g. an English query finding a Chinese note. Requires `pip install "piia-engram[vector]"`. Keyword search is used by default.keyword
ENGRAM_APPROVALNoSet to `strict` to gate every write behind user review. By default, high-risk items (credentials, shell commands, MCP config, permission rules) wait for review while low/medium writes are auto-absorbed but fully auditable and reversible.normal
ENGRAM_NO_UPDATE_CHECKNoSet to `1` to turn off the PyPI update check that the `engram` command performs at most once a day in interactive terminals.

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