Maestro MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ACEDATACLOUD_API_TOKEN | Yes | Your Ace Data Cloud API token. Get one from https://platform.acedata.cloud/console/applications |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| maestro_get_taskA | Get live progress and final outputs for one Maestro video task. |
| maestro_list_tasksB | List recent Maestro tasks owned by the authenticated user. |
| maestro_create_videoA | Create a complete video or iterate on a prior Maestro video. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| maestro_video_workflow | Explain the recommended Maestro workflow. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool targets a distinct action on the same resource: create a video task, fetch one task, list tasks. The descriptions reinforce the boundaries (create returns a task_id, get_task consumes it), leaving no realistic chance of misselection.
All three tools use the same maestro_ prefix followed by a consistent verb_noun pattern (create_video, get_task, list_tasks). Fully predictable and readable.
Three tools is on the lean side but each earns its place in the create-then-poll-then-list workflow for a narrow video-generation API. No filler or redundant tools are present.
The core lifecycle (submit job, poll progress, retrieve outputs, list history) is covered with no dead ends for the happy path. Minor gaps exist around cancelling/deleting a task and checking credit balance, which agents must work around.