Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
--hostNoHTTP bind address (default 127.0.0.1)
--httpNoserve Streamable HTTP instead of stdio
--portNoHTTP port (default 8765; 0 = pick a free port)
--tokenNobearer token (or TERMINAL_MCP_TOKEN; default: generated, saved to ~/.terminal-mcp/token)
--no-authNodisable auth (loopback binds only)
--max-waitNocap on any blocking wait in a tool call, in seconds (default 60)
--no-auditNodisable the audit log
--audit-logNoaudit log path (default ~/.terminal-mcp/audit.jsonl)
--url-tokenNoalso accept the token as a secret path /mcp/<token>
--allowed-hostNoextra Host header names to accept (your tunnel hostname)
--idle-timeoutNokill sessions untouched this long in minutes; 0 disables (default 60)
--keep-historyNolet agent commands into your shell history
--max-sessionsNomaximum running sessions (default 16)
--allow-any-hostNoaccept any Host header (token still required)
--allowed-originNoOrigin hostnames to accept from browser-based clients
TERMINAL_MCP_TOKENNoBearer token for HTTP mode (same as --token; default: generated and saved to ~/.terminal-mcp/token)

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