Skip to main content
Glama
tapra-ai
by tapra-ai

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TAPRA_API_KEYYesYour Tapra API key (starts with tapra_sk_live_…). Required.
TAPRA_API_URLNoForce an API origin, e.g. http://127.0.0.1:8787 for a local model host. Default: read from tapra.tn.
TAPRA_SITE_URLNoWebsite serving the price list, balance, and the current API address. Default: https://tapra.tn.
TAPRA_BASE_PATHNoInput files must be inside this folder; relative paths resolve here. Default: home folder.
TAPRA_OUTPUT_DIRNoWhere generated files go; outputs can't be written anywhere else. Default: ~/Tapra.
TAPRA_FFMPEG_PATHNoPath to ffmpeg if it is not on PATH. Default: ffmpeg.
TAPRA_AUDIO_PLAYERNoProgram play_audio runs as <player> <file>. Default: ffplay, then the system player.
TAPRA_MAX_COST_TNDNoRefuse any single call estimated above this amount. Default: none.
TAPRA_MCP_OUTPUT_MODENoOutput mode: files saves results; resources returns them inline only (nothing saved); both does both. Default: files.
TAPRA_TIMEOUT_SECONDSNoPer-request timeout. Default: 600.
TAPRA_MCP_MAX_INLINE_MBNoLargest file returned inline in resources / both mode. Default: 15.

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