Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoPort the server listens on8787
DOCS_DIRNoFolder with the tutorialsdocs
SITE_DIRNoLocal clone of the site repo. Turns on deploying from the connector (Docker sets it automatically)
DOCS_REPOYesThe docs repository in owner/name form
KEYS_FILENoFile that holds personal keys/data/keys.json
MCP_SECRETNoYour own connector key (24+ random characters). Needed for server mode unless you use only personal keys
PUBLIC_URLNoPublic address of the server, used to print personal connector URLs
ADMIN_TOKENNoTurns on the admin API; 24+ random characters
AUTO_DEPLOYNoRedeploy after every change. Set to false to leave it to deploy_sitetrue
DOCS_BRANCHNoBranch the site is built frommain
GITHUB_TOKENYesGitHub fine-grained personal access token with Contents: Read and write access to the docs repo
DEPLOY_COMMANDNoCommand that builds and publishes the site, run in SITE_DIR (use mkdocs gh-deploy for MkDocs)npm run deploy

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