Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoNative HTTP listener host. Docker sets host to 0.0.0.0 internally.127.0.0.1
PORTNoNative HTTP listener port.4310
API_TOKENNoOptional HTTP API bearer token. When set, requires a bearer token for /api/*. Health and metrics remain available to local scrapers.
MAX_IN_FLIGHTNoMaximum admitted running plus waiting scripts.4
SNAPSHOT_PATHNoEvidence JSON path, loaded and validated once at startup.data/snapshot.json
SANDBOX_WORKERSNoQuickJS worker count.2
SANDBOX_MEMORY_MBNoPer-sandbox memory limit in MB.64
SANDBOX_TIMEOUT_MSNoPer-execution SDK deadline in milliseconds.3000
SANDBOX_MAX_TOOL_CALLSNoTool-call budget per script.24

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