Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GFLOW_CLI_PROJECTNoDefault Flow project ID to use instead of creating a new project.
GFLOW_CLI_HEADLESSNoSet to 'true' to run Chrome with no window; experimental.
GFLOW_CLI_AUTO_RENEWNoSet to 'false' to disable automatic session renewal before submission.
GFLOW_CLI_OUTPUT_DIRNoWhere generated files go when no output path is passed.
GFLOW_CLI_WINDOW_MODENoControls Chrome window visibility, e.g. 'background' on macOS to run Chrome hidden without taking focus, 'offscreen' (default), or 'normal'.
GFLOW_CLI_JITTER_RANGENoPause range between batch submissions, e.g. '10-30'; widen it if you see WAF 403s.
GFLOW_CLI_LEASE_WAIT_SECONDSNoSeconds to wait for a profile that another gflow command is using instead of failing.

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