Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
JWT_SECRETYesRandom secret used to sign dashboard JWTs (e.g. generate with `openssl rand -hex 32`). Replace the placeholder before starting the stack.
ROUTING_PROVIDERNoRouting provider for skill matching. Set to `cloudflare` to use Cloudflare Workers AI, or `local` to point Snap at an already running System One-compatible model server.
LOCAL_SYSTEMONE_URLNoFull URL of the System One-compatible model server, e.g. http://YOUR_MODEL_HOST:30000/v1/systemone (required when ROUTING_PROVIDER=local). Use host.docker.internal for a model on the Docker host.
CLOUDFLARE_API_TOKENNoCloudflare Workers AI API token (required when ROUTING_PROVIDER=cloudflare).
CLOUDFLARE_ACCOUNT_IDNoCloudflare account ID (required when ROUTING_PROVIDER=cloudflare).
LOCAL_SYSTEMONE_MODELNoModel name expected by your System One endpoint, e.g. Cloudflare/clef-flash (required when ROUTING_PROVIDER=local).
SKILL_MATCH_THRESHOLDNoConfidence threshold for returning a matched skill; otherwise no match is returned.0.42
LOCAL_SYSTEMONE_API_KEYNoAPI key for the local model server. May be blank for a server without authentication (only used when ROUTING_PROVIDER=local).

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

Maintenance

ActivityMaintained
ResponsivenessNo issues