Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
AUTH_MODENoSet to `static` for local hacking without OAuth; uses GITHUB_TOKEN and a secret URL /mcp/<MCP_SECRET>. Do not use static mode for a public deployment.
READ_ONLYNoRead-only mode when FULL_CONTROL=false.
MCP_SECRETNoSecret URL segment used when AUTH_MODE=static.
PUBLIC_URLNoPublic URL of the service. Not needed on Render when RENDER_EXTERNAL_URL is available. Use http://localhost:3000 locally.
FULL_CONTROLNoDefaults to true, giving full control over every repo the token can reach. Set to false to enable ALLOWED_REPOS, READ_ONLY, and confirmation-gated destructive actions.true
GITHUB_TOKENNoGitHub token used when AUTH_MODE=static.
ALLOWED_REPOSNoAllowed repositories when FULL_CONTROL=false.
ENCRYPTION_KEYNoKey used to encrypt tokens. Render generates this automatically with the included blueprint; on other hosts set it yourself, e.g. with `openssl rand -base64 32`.
GITHUB_CLIENT_IDNoGitHub OAuth App client ID.
ALLOWED_GITHUB_USERSNoGitHub logins that are allowed to complete sign-in.
GITHUB_CLIENT_SECRETNoGitHub OAuth App client secret.
ALLOW_LOCALHOST_REDIRECTSNoSet to true for local runs to allow localhost redirects.

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