Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoBind address. `0.0.0.0` inside container (set automatically).127.0.0.1
PORTNoHTTP only. `npm run http` uses 8787.8080
API_KEYNoRegister one API key at boot.
MCP_URLNoCommand line client only: the server to talk to.http://127.0.0.1:8787/mcp
MCP_MODENoTransport mode: `stdio` or `http`.stdio
AUTH_MODENo`off` · `write` · `all`.off
MCP_USERSNoExtra logins, e.g. "alice:secret:read,write".
TENANT_IDNoIf set, writes need the `x-tenant-id` header.
ADMIN_USERNo`/admin` login user. Default disabled on a public bind until `ADMIN_PASSWORD` is set.demo
RATE_LIMITNoCalls per window per caller.60
MCP_API_KEYNostdio credential. The command line client sends it as a bearer key.
CORS_ORIGINSNoExtra `Origin` values allowed on `/mcp`. Localhost and same-host are always allowed.
MCP_PASSWORDNostdio basic auth password. The command line client sends them as HTTP Basic.
MCP_USERNAMENostdio basic auth username. The command line client sends them as HTTP Basic.
ADMIN_PASSWORDNo`/admin` login password. Required on a public bind (`HOST=0.0.0.0`, container, Code Engine) — the default is disabled there.demo
API_KEY_SCOPESNoScopes for the API key registered at boot.
RATE_LIMIT_WINDOW_MSNoRate limit window in milliseconds.60000

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