Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
hostNoHTTP host (default 127.0.0.1).127.0.0.1
pathYesPath to the project folder. The folder is created if it doesn't exist.
portNoHTTP port (default 8787, or the next free one).8787
allowNoReplace the command allowlist with a comma-separated list (e.g., npm,node,python).
stdioNoUse stdio transport (for Claude Desktop, Cursor, Claude Code).false
tokenNoSecret token (default: generated and saved).
tunnelNoOpen a public HTTPS URL for web AIs (cloudflared is downloaded automatically).false
read_onlyNoRead-only mode: no writes, no commands, nothing saved in the project.false
JECBRIDGE_TOKENNoSecret token (alternative to --token; default: generated and saved).
allow_all_commandsNoAllow any shell command (use with care).false

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