Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
MAX_USERSNoCaps active tokens. The check counts status = 'active' rows and runs on every issuance; re-issuing or rotating for an existing holder does not consume a seat.100
MCP_TOKENNoOptional break-glass master token (kdj_…) that bypasses D1 + quota. Not one of the metered seats.
JEV_API_KEYYesShared TypeSafe JEV API key — never exposed to clients, injected per request by the server and read in exactly one place (src/jev.ts). If missing the gateway still starts and /health reports degraded; tool calls fail with a 503 that names the missing secret.
ADMIN_PASSKEYNoGates /admin and /api/admin/* (constant-time compared, fails closed when unset). Accepted from the x-admin-passkey header or the JSON body; deliberately not accepted as a query parameter.

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