Skip to main content
Glama
AceDataCloud

Maestro MCP Server

Official
by AceDataCloud
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Maestro MCP Server

Produce complete videos from a natural-language brief with Maestro through the Ace Data Cloud API. Maestro plans the script, creates or sources media, generates voiceover and music, edits, captions, renders, and returns finished video variants.

Connect: hosted OAuth, API token, or local stdio

The hosted endpoint is https://maestro.mcp.acedata.cloud/mcp. Choose one route for the MCP client:

Route

When to use it

Credential setup

Hosted OAuth

The client supports remote MCP OAuth

Add only the URL, then sign in to AceDataCloud and approve access. No token needs to be pasted into client configuration.

Hosted API token

The client cannot finish OAuth, or you need an explicit integration credential

Send an AceDataCloud API token in the Authorization: Bearer … header. Keep it in a local secret store or environment variable.

Local stdio

The client runs a local MCP process

Install mcp-maestro and pass ACEDATACLOUD_API_TOKEN to that process. It still calls the AceDataCloud API.

The hosted service advertises OAuth metadata and Dynamic Client Registration (DCR). DCR registers the client application; it is not an API key. OAuth signs you in and the client sends the resulting Bearer token; it may reuse or create an API credential for the account. Browser sign-in still requires an AceDataCloud account. The hosted service can be metered: review current service documentation and displayed pricing before a real operation. Do not configure both an OAuth login and a fixed Authorization header for the same server.

Hosted OAuth examples

  • Claude and Claude Desktop chat: Add a remote custom connector in Customize → Connectors → Add custom connector, enter https://maestro.mcp.acedata.cloud/mcp, select sign-in, and choose Register automatically if Claude asks how to register its OAuth client. Complete consent. Claude Desktop's local claude_desktop_config.json is a separate setup. Claude connector guide.

  • Claude Code: claude mcp add --transport http --scope user maestro https://maestro.mcp.acedata.cloud/mcp, then claude mcp login maestro. Check /mcp. Claude Code MCP guide.

  • Cursor: Add a remote server with only https://maestro.mcp.acedata.cloud/mcp. For a project, merge the entry below into <project>/.cursor/mcp.json; for personal use, use ~/.cursor/mcp.json. Cursor MCP guide.

  • VS Code / Copilot: Run MCP: Add Server, select HTTP, enter https://maestro.mcp.acedata.cloud/mcp, then finish the browser sign-in. New portable workspace configs use <project>/.mcp.json; the VS Code-specific format below uses <project>/.vscode/mcp.json or the user profile. Check MCP: List Servers. VS Code MCP setup.

  • Codex: codex mcp add maestro --url https://maestro.mcp.acedata.cloud/mcp, then codex mcp login maestro. Its user settings are in ~/.codex/config.toml. Official Codex MCP guide.

Cursor project config (OAuth):

{
  "mcpServers": {
    "maestro": {"url": "https://maestro.mcp.acedata.cloud/mcp"}
  }
}

VS Code-specific workspace config (OAuth):

{
  "servers": {
    "maestro": {"type": "http", "url": "https://maestro.mcp.acedata.cloud/mcp"}
  }
}

Hosted API token

Sign in at AceDataCloud Platform, open the service page, and obtain an API credential. A fixed Bearer header is useful when your client lacks OAuth; an invalid header does not fall back to OAuth in Claude Code. The header value is sensitive, so keep it out of committed files and screenshots.

For Claude Code, the shell expands the token when you add the server; treat the saved user MCP config as a secret:

export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
claude mcp add --transport http --scope user maestro https://maestro.mcp.acedata.cloud/mcp \
  --header "Authorization: Bearer $ACEDATACLOUD_API_TOKEN"

For a Claude Code project config, put a variable reference in <project>/.mcp.json and set that variable in the environment that launches Claude Code:

{
  "mcpServers": {
    "maestro": {
      "type": "http",
      "url": "https://maestro.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${ACEDATACLOUD_API_TOKEN}"}
    }
  }
}

Cursor uses a different environment-variable syntax in ~/.cursor/mcp.json or an uncommitted project config:

{
  "mcpServers": {
    "maestro": {
      "url": "https://maestro.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${env:ACEDATACLOUD_API_TOKEN}"}
    }
  }
}

In VS Code, run MCP: Open User Configuration and merge this server plus its masked input; ${input:...} is for VS Code's user/workspace format and is not portable to the Agent Host .mcp.json format:

{
  "inputs": [
    {"id": "acedata-maestro-token", "type": "promptString", "description": "AceDataCloud API token", "password": true}
  ],
  "servers": {
    "maestro": {
      "type": "http",
      "url": "https://maestro.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${input:acedata-maestro-token}"}
    }
  }
}

For Cline, use its MCP configuration UI or CLI file ~/.cline/data/settings/cline_mcp_settings.json; its remote transport value is streamableHttp. For JetBrains AI Assistant, add a remote URL from Settings → Tools → AI Assistant → Model Context Protocol (MCP). For Zed, use a context_servers entry with the URL only for OAuth or add a local Bearer header. These clients have different configuration schemas; follow their current UI rather than copying another client's JSON. Cline · JetBrains · Zed.

Local stdio

Install the package and give the local process an API token:

python -m pip install mcp-maestro
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
mcp-maestro

For Claude Desktop local MCP, merge this entry into the file opened by its developer settings (~/Library/Application Support/Claude/claude_desktop_config.json on macOS). uvx requires uv on PATH:

{
  "mcpServers": {
    "maestro": {
      "command": "uvx",
      "args": ["mcp-maestro"],
      "env": {"ACEDATACLOUD_API_TOKEN": "YOUR_API_TOKEN"}
    }
  }
}

Keep this user-level file private. Self-hosted HTTP uses mcp-maestro --transport http --port 8000; expose it only with suitable network and TLS controls. Local execution still calls the AceDataCloud API.

Check before using the service

  1. https://maestro.mcp.acedata.cloud/health returning {"status":"ok"} checks endpoint reachability only.

  2. Confirm that the MCP client loads tools. The tool list shows MCP discovery, not downstream API access or balance.

  3. If you need a full API check, call maestro_create_video with your own valid input after reviewing current service documentation and displayed pricing. If the result contains a task ID, call maestro_get_task on that same ID until terminal success or failure. Do not resubmit the operation just to check progress.

For 401, check which auth route the client used and whether the token or OAuth session is valid. A 403 may mean an account permission or content moderation failure; read the returned error. Insufficient balance and downstream service failures need their own diagnosis. A listed tool or submitted task does not prove a successful result.

Related MCP server: Happy Horse MCP Server

Tools

Tool

Purpose

maestro_create_video

Create a video or run remix, edit, or extend on an earlier task

maestro_get_task

Read progress, status, and final language variants for one task

maestro_list_tasks

List the authenticated account's recent tasks, newest first

Example

Ask an MCP client:

Create a 45-second 16:9 English product launch video from this product photo. Use an editorial style and a documentary voice.

The tool returns a task_id immediately. Query that ID until status is succeeded or failed. Successful tasks expose videos in response.data.variants.

To inspect existing task history without creating a video, call maestro_list_tasks. It accepts a limit from 1 to 100 and optional exclusive created_at_min / created_at_max Unix timestamp bounds. The returned items honor those filters; count remains the authenticated account's total visible task count.

Production contract

Maestro provides the complete capability set on every request: all actions and scenarios, 5–300 seconds, up to 4 languages, and 1080p/30fps output. Pricing can change by scenario, duration, and output languages; check the current Maestro pricing before submitting. Task polling does not submit a new generation.

To revise an existing result, call maestro_create_video with an iteration action and the prior task ID:

{
  "prompt": "Keep the visuals but tighten the first 10 seconds and use a warmer voice.",
  "action": "edit",
  "ref_task_id": "previous-task-id"
}

MCP Client Configuration

{
  "mcpServers": {
    "maestro": {
      "command": "uvx",
      "args": ["mcp-maestro"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your-token"
      }
    }
  }
}

Development

pip install -e ".[dev,test,release]"
pytest --cov=core --cov=tools
ruff check .
ruff format --check .
mypy core tools main.py
python -m build

See the Maestro API documentation for billing and response details.

Documentation

Documentation

Available Tools

3 tools
maestro_create_videoAInspect

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

The call returns immediately with a task_id. Use maestro_get_task to monitor progress and obtain
each completed language variant's output_url, captions_url, cover_url, duration, and QC score.
ParametersJSON Schema
NameRequiredDescriptionDefault
langsNoOutput language codes, such as zh-cn, en, ja, or pt-br. Each language produces a localized video variant.
styleNoVisual 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.
voiceNoNarration voice preset. Use 'auto' or omit to let the server decide.
actionNogenerate creates a new video. remix, edit, and extend iterate on a previous Maestro task and require ref_task_id.generate
aspectNoOutput 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.
promptYesNatural-language production brief: topic, audience, scenes, tone, and desired outcome. Maestro plans the script, assets, voiceover, edit, captions, and render.
durationNoTarget 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.
scenarioNoProduction 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_urlsNoReference image, video, or audio URLs for Maestro to use.
ref_task_idNoPrevious Maestro task ID for remix, edit, or extend.
callback_urlNoOptional webhook URL called when the task succeeds or fails.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the key non-obvious behavior: the call is asynchronous and returns immediately with a task_id, with progress and results available only through another tool. It could add failure/reversibility details, but the async handoff is well communicated.

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?

Two tight sentences: the first states the core action, the second covers the async contract and points to the monitoring sibling. No filler or redundancy; every sentence earns its place.

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 11-parameter tool with rich schema coverage and an output schema, the description is nearly sufficient: it sets expectations for async invocation and result retrieval. It could briefly mention the iteration dependency on ref_task_id, but that is already fully documented in the schema and action parameter.

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 baseline is 3. The description itself adds no parameter-level detail beyond what the schema already documents, but it doesn't need to; the schema provides thorough meaning for all 11 parameters.

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 uses a specific verb ('Create') with a clear resource ('a complete video') and explicitly covers the iterate-on-prior case, distinguishing it cleanly from the only sibling, maestro_get_task. No ambiguity about what this tool produces.

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

Usage Guidelines5/5

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

The description states the asynchronous flow: this tool returns immediately with task_id, then directs the agent to maestro_get_task for monitoring and output retrieval. It gives explicit routing to the alternative tool and makes the division of labor clear.

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

maestro_get_taskAInspect

Get live progress and final outputs for one Maestro video task.

ParametersJSON Schema
NameRequiredDescriptionDefault
task_idYesTask ID returned by maestro_create_video.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. The verb 'Get' clearly implies a read-only operation, and it mentions 'live progress' suggesting polling. However, it doesn't explicitly state side-effect-freeness, error behavior, or rate limits. It provides baseline transparency but lacks depth.

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?

The description is a single sentence, front-loaded with the action and resource, and contains no filler. Every word adds value.

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

Completeness5/5

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

For a simple get-by-ID tool with one parameter and an output schema present, the description sufficiently states what it does and what it returns. It is complete for the tool's complexity and relies appropriately on the output schema for return details.

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?

The schema description already covers the task_id parameter fully (100% coverage), with a clear description 'Task ID returned by maestro_create_video.' The tool description does not add additional parameter semantics beyond the schema, so the baseline of 3 is appropriate.

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 uses the specific verb 'Get' with a clear resource ('live progress and final outputs for one Maestro video task'). It explicitly scopes to a single task, distinguishing it from siblings like 'maestro_list_tasks' (listing) and 'maestro_create_video' (creating).

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?

The phrase 'for one Maestro video task' clearly implies this is for a single task, contrasting with the sibling list tool. It does not explicitly state 'when not to use' or name alternatives, but the context is clear enough for an agent to decide.

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

maestro_list_tasksAInspect

List recent Maestro tasks owned by the authenticated user.

ParametersJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of recent tasks to return.
created_at_maxNoOnly include tasks created strictly before this Unix timestamp.
created_at_minNoOnly include tasks created strictly after this Unix timestamp.

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.8/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses ownership scope and recency, and 'List' implies a read-only operation, but it does not describe ordering, pagination, or result bounding beyond the schema. This is acceptable but minimal for a read-only list.

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?

The description is a single sentence with no wasted words. The key facts—action, resource, ownership, and recency—are front-loaded and immediately useful.

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 a simple list tool with a full output schema and complete parameter documentation, the one-line description is largely sufficient. It does not include explicit usage guidance or alternatives, but the purpose and sibling names cover the main decision an agent needs to make.

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%: all three parameters (`limit`, `created_at_max`, `created_at_min`) already have meaningful descriptions in the schema. The description adds no parameter-specific meaning, so the baseline of 3 applies.

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 uses a specific verb ('List') with a clear resource ('Maestro tasks') and scopes it to tasks owned by the authenticated user. This clearly differentiates it from the sibling tools `maestro_create_video` and `maestro_get_task`.

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

Usage Guidelines3/5

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

The basic use case is implied by the purpose—use this to list recent tasks—but there is no explicit guidance about when to prefer it over `maestro_get_task` or when not to use it. The agent must infer the boundary from sibling names and the verb.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.1.4
    • Addedmaestro_list_tasks
  2. 1 tool updatev0.1.3
    • Changedmaestro_create_video2 fields changed
      • 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"
-}
  3. 2 tool updatesv0.1.2
    • Changedmaestro_create_video1 field changed
      • 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"
-}
    • Removedmaestro_list_tasks
  4. 1 tool updatev0.1.1
    • Changedmaestro_create_video12 fields changed
      • 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."
  5. 3 tool updatesv0.1.0
    • First observedmaestro_create_video
    • First observedmaestro_get_task
    • First observedmaestro_list_tasks
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored across 3 tools

Disambiguation5/5

Each tool covers a distinct operation: listing tasks, creating a video, and retrieving task status/outputs. There is no overlap between creating, listing, and fetching a single task.

Naming Consistency5/5

All tool names follow the same verb_noun pattern with snake_case: list_tasks, create_video, get_task. The naming is uniform and predictable across the set.

Tool Count4/5

Three tools is a minimal but valid set for the video creation workflow. The count is slightly low, but each tool is necessary for the core create-monitor-retrieve flow.

Completeness4/5

The surface covers the full lifecycle for a video task: create, list, and get results. Minor gaps exist such as cancel/delete or updating task parameters, but the primary workflow is fully supported.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers