Maestro MCP Server

Official

Overview Schema Source Related Servers Discussions Admin

maestro_create_video

Create a complete video from a natural-language prompt or iterate on a prior Maestro video. Specify language, style, voice, aspect, and duration; get a task ID for tracking.

Instructions

Create a complete video or iterate on a prior Maestro video.

One task delivers one video in one language. Successful jobs cost 0.7 Credits per actual
delivered second, never above the requested duration, with no scenario or language surcharge.
Failed jobs and task polling are free.

The call returns immediately with a task_id. Use maestro_get_task to monitor progress and obtain
the completed video's output_url, captions_url, cover_url, duration, and QC score.

Input Schema

Name	Required	Description	Default
`langs`	No	Exactly one output language code per task, such as zh-cn, en, ja, or pt-br.
`style`	No	Visual style preset. Named presets: cinematic, glass, luxury, swiss, modern, editorial, warm, vibrant, neon, mono, pastel, bold, industrial, futuristic, retro. Use 'auto' or omit to let the server decide.
`voice`	No	Narration voice preset. Use 'auto' or omit to let the server decide.
`action`	No	generate creates a new video. remix, edit, and extend iterate on a previous Maestro task and require ref_task_id.	generate
`aspect`	No	Output aspect ratio: 9:16, 16:9, or 1:1. Omit to use the server default (9:16) on a new video, or to inherit the source task's ratio when iterating.
`prompt`	Yes	Natural-language production brief: topic, audience, scenes, tone, and desired outcome. Maestro plans the script, assets, voiceover, edit, captions, and render.
`duration`	No	Target video duration in seconds, from 5 to 300. Omit to use the server default (30) on a new video, or to inherit the source task's duration when iterating.
`scenario`	No	Production workflow: auto, narrated, captions, avatar, or drama. Captions requires a source video in file_urls. Avatar normally needs a portrait in file_urls. Omit to let the server decide.
`file_urls`	No	Reference image, video, or audio URLs for Maestro to use.
`ref_task_id`	No	Previous Maestro task ID for remix, edit, or extend.
`callback_url`	No	Optional webhook URL called when the task succeeds or fails.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.1.6Oct 20, 2026

changedInput schema / properties / langs / anyOf

Previous value: -[
-  {
-    "items": {
-      "type": "string"
-    },
-    "maxItems": 4,
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "maxItems": 1,
+    "minItems": 1,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / langs / description

Previous value: -"Output language codes, such as zh-cn, en, ja, or pt-br. Each language produces a localized video variant."New value: +"Exactly one output language code per task, such as zh-cn, en, ja, or pt-br."

Changed2 schema fields changedv0.1.3Sep 5, 2026

changedInput schema / properties / file_urls / anyOf

Previous value: -[
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "maxItems": 20,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

removedInput schema / properties / quality

Removed value: -{
-  "anyOf": [
-    {
-      "enum": [
-        "lite",
-        "standard",
-        "pro"
-      ],
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Production tier: lite, standard, or pro. Omit to use the server default (standard) on a new video, or to inherit the source task's tier when iterating.",
-  "title": "Quality"
-}

Changed1 schema field changedv0.1.2Aug 24, 2026

removedInput schema / properties / task_id

Removed value: -{
-  "anyOf": [
-    {
-      "format": "uuid",
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Optional client-generated UUID. Reusing it is rejected; omit it to let the server generate a task ID.",
-  "title": "Task Id"
-}

Changed12 schema fields changedv0.1.1Aug 17, 2026

changedInput schema / properties / duration / anyOf

Previous value: -[
-  {
-    "maximum": 600,
-    "minimum": 1,
-    "type": "integer"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "maximum": 300,
+    "minimum": 5,
+    "type": "integer"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / duration / description

Previous value: -"Target video duration in seconds, from 1 to 600. Omit to use the server default (30) on a new video, or to inherit the source task's duration when iterating."New value: +"Target video duration in seconds, from 5 to 300. Omit to use the server default (30) on a new video, or to inherit the source task's duration when iterating."

changedInput schema / properties / langs / anyOf

Previous value: -[
-  {
-    "items": {
-      "type": "string"
-    },
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "type": "string"
+    },
+    "maxItems": 4,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / quality / anyOf

Previous value: -[
-  {
-    "enum": [
-      "draft",
-      "standard",
-      "premium"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "lite",
+      "standard",
+      "pro"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / quality / description

Previous value: -"Production tier: draft, standard, or premium. Omit to use the server default (standard) on a new video, or to inherit the source task's tier when iterating."New value: +"Production tier: lite, standard, or pro. Omit to use the server default (standard) on a new video, or to inherit the source task's tier when iterating."

changedInput schema / properties / scenario / anyOf

Previous value: -[
-  {
-    "enum": [
-      "auto",
-      "narrated",
-      "drama",
-      "avatar",
-      "motion",
-      "slideshow"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "auto",
+      "narrated",
+      "captions",
+      "avatar",
+      "drama"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / scenario / description

Previous value: -"Production workflow: auto, narrated, drama, avatar, motion, or slideshow. Avatar normally needs a portrait in file_urls. Omit to let the server decide."New value: +"Production workflow: auto, narrated, captions, avatar, or drama. Captions requires a source video in file_urls. Avatar normally needs a portrait in file_urls. Omit to let the server decide."

changedInput schema / properties / style / anyOf

Previous value: -[
-  {
-    "enum": [
-      "auto",
-      "cinematic",
-      "glass",
-      "luxury",
-      "swiss",
-      "modern",
-      "editorial",
-      "warm",
-      "vibrant",
-      "neon",
-      "mono",
-      "pastel",
-      "bold",
-      "industrial",
-      "futuristic",
-      "retro"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "auto",
+      "cinematic",
+      "glass",
+      "luxury",
+      "swiss",
+      "modern",
+      "editorial",
+      "warm",
+      "vibrant",
+      "neon",
+      "mono",
+      "pastel",
+      "bold",
+      "industrial",
+      "futuristic",
+      "retro"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / style / description

Previous value: -"Visual style preset or freeform style hint. Named presets: cinematic, glass, luxury, swiss, modern, editorial, warm, vibrant, neon, mono, pastel, bold, industrial, futuristic, retro. Use 'auto' or omit to let the server decide."New value: +"Visual style preset. Named presets: cinematic, glass, luxury, swiss, modern, editorial, warm, vibrant, neon, mono, pastel, bold, industrial, futuristic, retro. Use 'auto' or omit to let the server decide."

addedInput schema / properties / task_id

Added value: +{
+  "anyOf": [
+    {
+      "format": "uuid",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional client-generated UUID. Reusing it is rejected; omit it to let the server generate a task ID.",
+  "title": "Task Id"
+}

changedInput schema / properties / voice / anyOf

Previous value: -[
-  {
-    "enum": [
-      "auto",
-      "warm-female",
-      "bright-female",
-      "anchor-female",
-      "clean-female",
-      "calm-male",
-      "deep-male",
-      "documentary-male",
-      "energetic-male",
-      "storyteller-male"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "auto",
+      "warm-female",
+      "bright-female",
+      "anchor-female",
+      "clean-female",
+      "calm-male",
+      "deep-male",
+      "documentary-male",
+      "energetic-male",
+      "storyteller-male"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / voice / description

Previous value: -"Narration voice preset, auto, or a 32-hex-character Fish reference ID. Omit to let the server decide."New value: +"Narration voice preset. Use 'auto' or omit to let the server decide."

First observedv0.1.0Aug 1, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does so well: it discloses asynchronous behavior ('returns immediately with a task_id'), the credit cost model (0.7 per delivered second, capped at requested duration), no scenario/language surcharge, and that failed jobs and polling are free. It stops short of stating auth/permission needs or concurrency limits, keeping it out of the top band.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight paragraphs: capability first, cost/pricing second, async contract third. Every sentence carries information an agent needs and nothing is repeated from the schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an async generation tool with 11 parameters and an output schema, the description covers the critical gaps: it explains the async task_id handoff, cost exposure, and success/failure economics. Output fields are already covered by the output schema, so its omission there is appropriate; permission/error semantics are the only unaddressed area.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already explains prompt, action, ref_task_id, aspect, duration, scenario, and the presets. The description only reinforces the single-language constraint already encoded as maxItems:1 on langs, adding little semantic value beyond the schema baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource ('Create a complete video') and adds the iterate-on-a-prior-video case. It also names the sibling maestro_get_task for monitoring, so an agent can distinguish creation from the read/monitor tools without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear operating context: one task delivers one video in one language, and polling/progress goes through maestro_get_task. There is no explicit 'do not use this when...' carve-out, but the generate-vs-iterate routing and the monitor handoff are unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server