Shadow Music Generator
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| YUE_ABC | No | YuE ABC notation | |
| YUE_COT | No | YuE chain-of-thought mode (full/melody/off) | |
| YUE_VAE | No | YuE VAE path or identifier | |
| YUE_SEED | No | YuE random seed | |
| YUE_MODEL | No | YuE model to use | m-a-p/YuE2-3B |
| YUE_DEVICE | No | Device for YuE (e.g. cuda, cpu) | |
| YUE_LYRICS | No | YuE lyrics | |
| YUE_COMMAND | No | Command template for remote YuE execution, e.g. ssh gpu 'yue2 generate --request {request_json} --output {output_dir}' | |
| YUE_OUTPUTS | No | YuE outputs | |
| SHADOW_JOB_DIR | No | Where job files are stored | ./.shadow-jobs |
| YUE_REQUEST_JSON | No | YuE request JSON | |
| SHADOW_PIPELINE_FACTORY | No | module:callable or /path/file.py:callable adapter for local runs |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| submit_generationC | Queue a Shadow Music Generator job. Dry-run validates the request and never runs a model. |
| run_jobC | Run a queued job through the configured SHADOW_PIPELINE_FACTORY adapter. |
| job_statusB | Read one job: status, stages, outputs, model license and errors. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clear distinct purpose: submit_generation queues jobs, run_job executes queued jobs, job_status reads job state. No overlap.
All lower snake_case, but submit_generation is verb_noun while run_job is verb_noun and job_status is noun_noun. Minor inconsistency in pattern.
Three tools perfectly cover the basic lifecycle of submitting, running, and checking a job. Well-scoped, no excess.
Covers submit, run, and status, but missing operations like listing jobs, canceling jobs, or timeout handling. Notable gaps for a job queue system.