Schema | audiolla

audiolla

Overview Schema Related Servers Score Discussions

Server Configuration

Describes the environment variables required to run the server.

Name	Required	Description	Default
`HF_TOKEN`	No	HuggingFace access token. Required for gated engines such as pyannote, stable-audio-open, musicgen-small, and musicgen-medium.
`LOG_LEVEL`	No	Log level: DEBUG, INFO, WARNING, ERROR, or CRITICAL.	INFO
`AUDIOLLA_DEVICE`	No	Device to use: auto, cpu, cuda, or cuda:N.	auto
`AUDIOLLA_JOB_TTL`	No	Seconds a completed, failed, or cancelled async job remains in memory before being swept.	3600
`AUDIOLLA_PRELOAD`	No	Comma-separated engine slugs to load into memory at startup.
`AUDIOLLA_DATA_DIR`	No	Directory where models and staged files live.	/data
`HUGGINGFACE_TOKEN`	No	Alias for HF_TOKEN. The entrypoint mirrors both names, so setting either works.
`AUDIOLLA_SOUNDFONT`	No	Default SoundFont path used by /v1/midi/render.	/usr/share/sounds/sf2/FluidR3_GM.sf2
`AUDIOLLA_AUTH_TOKEN`	No	Bearer token for authenticating requests; empty means no auth.
`AUDIOLLA_ENGINE_TTL`	No	Seconds an engine stays loaded after being idle before it is unloaded.	600
`AUDIOLLA_FETCH_MODE`	No	Server-side fetching policy: disabled, allowlist, or denylist.	disabled
`AUDIOLLA_FETCH_HOSTS`	No	Comma-separated host patterns allowed for fetching when AUDIOLLA_FETCH_MODE is allowlist.
`AUDIOLLA_PRESETS_DIR`	No	Directory containing YAML preset workflows loaded at startup.	/app/presets
`AUDIOLLA_ENGINES_FILE`	No	Path to the engines registry file.	/app/engines.json
`AUDIOLLA_LOAD_TIMEOUT`	No	Seconds allowed for an engine's cold load before it is treated as failed.	300
`AUDIOLLA_FETCH_SCHEMES`	No	Comma-separated URL schemes permitted for fetching (https, http).	https
`AUDIOLLA_FETCH_TIMEOUT`	No	Hard timeout in seconds for each fetch or upload.	30
`AUDIOLLA_UVR_MODELS_DIR`	No	Directory where UVR model files are cached.	/data/uvr_models
`AUDIOLLA_ENABLED_ENGINES`	No	Comma-separated engine slugs to allow; empty means all engines are enabled.
`AUDIOLLA_MAX_UPLOAD_BYTES`	No	Maximum upload size in bytes (200 MB); also caps URL fetch body size.	209715200
`AUDIOLLA_SWEEPER_INTERVAL`	No	Seconds between idle engine sweeper checks.	60
`AUDIOLLA_JOB_MAX_CONCURRENT`	No	Maximum concurrent async jobs (parsed at startup; not yet enforced).	8
`AUDIOLLA_FETCH_ALLOW_PRIVATE`	No	Whether to allow URLs that resolve to private, loopback, or link-local IP addresses.	false
`AUDIOLLA_FETCH_MAX_REDIRECTS`	No	Maximum number of redirects followed for each fetch.	5
`AUDIOLLA_ENABLE_NONCOMMERCIAL`	No	Set to 1 to enable non-commercial engines such as MusicGen and matchering.

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

Name	Description
No tools

Prompts

Interactive templates invoked by user choice

Name	Description
No prompts

Resources

Contextual data attached and managed by the client

Name	Description
No resources

Server Configuration
Instructions
Capabilities
Tools
Prompts
Resources

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/psyb0t/docker-audiolla'

If you have feedback or need assistance with the MCP directory API, please join our Discord server