Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GIS_API_PORTNoPort for the HTTP API server (`gis-assistant-api`).8100
GIS_API_TOKENNoBearer token for HTTP API authentication. If unset, a random token is generated at startup and printed to stdout.
GIS_WORKSPACENoOutput directory. All output paths are resolved and confined to this workspace.~/gis-workspace
OPENAI_API_KEYNoOpenAI API key, read by the OpenAI SDK. Required when `GIS_PLANNER_PROVIDER=openai`; needs the `openai` extra installed. Not required for execution-only tools (`gis.run_plan`, `gis.resume`, `gis.list_capabilities`, `gis.explain_last_run`, `gis.qgis_status`).
ANTHROPIC_API_KEYNoAnthropic API key, read by the Anthropic SDK. Required when using the Claude (default) provider for plan generation (`gis.plan`, `gis.answer`, `gis.run`, `gis.diagnose`).
GIS_PLANNER_MODELNoOverrides the provider default model (`claude-opus-5` or `gpt-4o`). Must match the selected provider; a mismatch is logged as a warning.
GIS_PLANNER_PROVIDERNoThe LLM provider used to generate plans. `anthropic` (aliases: `claude`) or `openai` (aliases: `chatgpt`, `gpt`). Claude is the default.anthropic

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