Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HOSTNoListening address. (Hosted mode)0.0.0.0
PORTNoListening port. (Hosted mode)8080
AUDIO_DIRNoWhere audio is kept until it expires. (Hosted mode)<tmp>/bakbak-mcp-audio
AUDIO_TTLNoHow long audio links work: seconds, or 90s, 30m, 1h. (Hosted mode)1h
LOG_LEVELNodebug, info, warn or error. Logs are JSON lines on stderr; stdout carries only the protocol.info
BAKBAK_API_KEYNoYour API key. Without it the server still starts and lists its tools; every call explains how to set the key. (Local mode)
MCP_PUBLIC_URLNoPublic origin, e.g. https://mcp.bakbak.si. Every advertised URL is built from it, never from the Host header. Required for hosted mode (bakbak-mcp --http).
AUDIO_MAX_BYTESNoCap on stored audio; the oldest files go first. Bytes, or 512M, 2G. (Hosted mode)2G
BAKBAK_BASE_URLNoAPI base URL, for example a staging deployment.https://hub.getraya.app
TRUSTED_PROXIESNoCIDRs of reverse proxies whose CF-Connecting-IP / X-Forwarded-For are believed (for per-address rate limits). Empty trusts none. (Hosted mode)loopback and private ranges
MAX_OUTPUT_BYTESNoMost audio one text_to_speech call may produce, estimated from the text before any credits are spent. (Hosted mode)512M
MCP_TOKEN_SECRETNoSecret for sealing OAuth tokens: at least 32 characters (openssl rand -base64 48). Rotate with new_kid:new_secret,old_kid:old_secret: the first seals, all open. Required for hosted mode (bakbak-mcp --http).
INFLIGHT_AUDIO_BYTESNoMost estimated audio being produced at once across all calls; at least MAX_OUTPUT_BYTES. (Hosted mode)1G
BAKBAK_MCP_OUTPUT_DIRNoWhere new audio files go. Created when needed; ~ is expanded. (Local mode)~/Documents/Bakbak (or ~/Bakbak if there is no Documents)
AUDIO_MAX_BYTES_PER_KEYNoStored audio per API key; a key's own oldest files go first, so one key cannot push out everyone else's links. (Hosted mode)a quarter of AUDIO_MAX_BYTES
TTS_CONCURRENCY_PER_KEYNoMost text_to_speech calls running at once per API key. (Hosted mode)2

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