Skip to main content
Glama

ProducerMCP

PyPI version PyPI downloads Python 3.10+ License: MIT MCP

A Model Context Protocol (MCP) server for AI music generation using Producer/Riffusion (FUZZ models) through the AceDataCloud API.

Generate AI music directly from Claude, VS Code, or any MCP-compatible client.

Features

  • Text to Music - Create AI-generated music from text prompts

  • Custom Music - Full control with custom lyrics, title, and style

  • Song Extension - Continue songs from any timestamp

  • Cover/Remix - Create covers in different genres and styles

  • Variations - Generate alternative versions of songs

  • Vocal/Instrumental Swap - Mix vocals and instrumentals between songs

  • Section Replacement - Re-generate specific sections of a song

  • Stem Separation - Split songs into vocal and instrumental tracks

  • Lyrics Generation - Generate structured lyrics from prompts

  • Video Generation - Create music videos for songs

  • WAV Export - Get lossless audio format

  • 8 FUZZ Models - From FUZZ-0.8 to FUZZ-2.0 Pro

Related MCP server: SunoMCP

Tool Reference

Tool

Description

producer_generate_music

Generate AI music from a text prompt.

producer_generate_custom_music

Generate music with custom lyrics, title, and style.

producer_extend_music

Extend an existing song from a specific timestamp.

producer_cover_music

Create a cover/remix version in a different style.

producer_variation_music

Create a variation of an existing song.

producer_swap_vocals

Swap vocals between two songs.

producer_swap_instrumentals

Swap instrumentals between two songs.

producer_replace_section

Replace a specific time range with new content.

producer_stems_music

Separate a song into vocal and instrumental stems.

producer_generate_lyrics

Generate structured song lyrics from a prompt.

producer_upload_audio

Upload external audio for processing.

producer_generate_video

Generate a music video for a song.

producer_generate_wav

Get lossless WAV format of a song.

producer_get_task

Query the status of a generation task.

producer_get_tasks_batch

Query multiple generation tasks at once.

producer_list_models

List all available FUZZ models.

producer_list_actions

List all available actions and tools.

producer_get_lyric_format_guide

Get lyrics formatting guide.

Connect: hosted OAuth, API token, or local stdio

The hosted endpoint is https://producer.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-producer 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://producer.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 producer https://producer.mcp.acedata.cloud/mcp, then claude mcp login producer. Check /mcp. Claude Code MCP guide.

  • Cursor: Add a remote server with only https://producer.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://producer.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 producer --url https://producer.mcp.acedata.cloud/mcp, then codex mcp login producer. Its user settings are in ~/.codex/config.toml. Official Codex MCP guide.

Cursor project config (OAuth):

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

VS Code-specific workspace config (OAuth):

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

Hosted API token

  1. Open Ace Data Cloud → Applications. Sign in, or register an account first.

  2. Find General application. If it has not been created, choose Initialize General Application. A general key can use the services available to your account; a dedicated application's key is limited to its service. Check the required service/model access and current pricing.

  3. Copy the API Key from the application card, or open Keys / Manage Keys → Create to create a separate key for this integration. Give it a recognizable name so you can revoke or rotate it independently.

  4. When creating a key, review Expiration Time, Set Usage Limitation, and Allowed APIs. Enable only the restrictions you need, allow the operations you will call, then click Create and copy the token from the key list. Task lookup does not grant permission to submit a generation. Confirm the application's balance can cover your first request; any trial allowance is whatever your account currently displays.

  5. Copy only the token value, without quotation marks, spaces, or Bearer . An API Key / API Token field expects this raw value; only a manually configured HTTP Authorization header needs the Bearer prefix. A platform-... account-management token cannot replace a generation API key.

Copy an application API key or open Manage Keys

Create a separately named key with optional restrictions

Save the key in the client's credential store or the environment variable shown below. Never put it in a prompt, shared workflow, screenshot, or Git commit. If authentication fails, check the full copied value, application/service access, expiration, usage limit, and balance before creating another key.

A fixed Bearer header bypasses OAuth. If the header is invalid, remove it before trying browser sign-in; keep the saved credential private.

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 producer https://producer.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": {
    "producer": {
      "type": "http",
      "url": "https://producer.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": {
    "producer": {
      "url": "https://producer.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-producer-token", "type": "promptString", "description": "AceDataCloud API token", "password": true}
  ],
  "servers": {
    "producer": {
      "type": "http",
      "url": "https://producer.mcp.acedata.cloud/mcp",
      "headers": {"Authorization": "Bearer ${input:acedata-producer-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-producer
export ACEDATACLOUD_API_TOKEN='YOUR_API_TOKEN'
mcp-producer

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

Keep this user-level file private. Self-hosted HTTP uses mcp-producer --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://producer.mcp.acedata.cloud/health returning {"status":"ok"} checks endpoint reachability only.

  2. Confirm that the MCP client loads tools. producer_list_models is a reference tool; it does not verify downstream API access or balance.

  3. If you need a full API check, call producer_generate_music with your own valid input after reviewing current service documentation and displayed pricing. If the result contains a task ID, call producer_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.

Available Tools

Music Generation

Tool

Description

producer_generate_music

Generate music from a text prompt

producer_generate_custom_music

Generate with custom lyrics and style

producer_extend_music

Extend a song from a timestamp

producer_cover_music

Create a cover in a different style

producer_variation_music

Create a variation of a song

Vocal/Instrumental

Tool

Description

producer_swap_vocals

Swap vocals between two songs

producer_swap_instrumentals

Swap instrumentals between two songs

producer_replace_section

Replace a time range with new content

producer_stems_music

Separate into stems

Lyrics

Tool

Description

producer_generate_lyrics

Generate lyrics from a prompt

Media

Tool

Description

producer_upload_audio

Upload external audio

producer_generate_video

Generate video for a song

producer_generate_wav

Get lossless WAV format

Tasks

Tool

Description

producer_get_task

Query a single task status

producer_get_tasks_batch

Query multiple tasks at once

Information

Tool

Description

producer_list_models

List available FUZZ models

producer_list_actions

List available API actions

producer_get_lyric_format_guide

Lyric formatting guide

Action-specific inputs

producer_generate_music requires a prompt. For custom vocals, supply lyric to producer_generate_custom_music; for custom instrumental music, set instrumental=true and omit lyrics and prompt. A title is optional. producer_extend_music needs audio_id and a positive continue_at; it also needs lyrics unless instrumental=true. Lyrics on extensions and replacements select custom mode. Covers, variations, swaps and stem separation need the source audio_id, not placeholder lyrics or prompts. Omitted lyrics_strength and sound_strength use the API defaults (0.5).

Usage Examples

Generate Music from Prompt

User: Create a jazz song about rainy nights

Claude: I'll generate a jazz song for you.
[Calls producer_generate_music with prompt="Smooth jazz song about rainy nights, saxophone, piano, moody"]

Custom Song with Lyrics

User: Here are my lyrics:
[Verse] Walking in the rain...
[Chorus] But I keep moving on...

Claude: I'll create a song with your lyrics.
[Calls producer_generate_custom_music with lyrics, title, and prompt]

Extend a Song

User: Make this song longer with another verse

Claude: I'll extend the song from where it left off.
[Calls producer_extend_music with audio_id, continue_at, and new lyrics]

Create a Cover

User: Make an acoustic version of this song

Claude: I'll create an acoustic cover.
[Calls producer_cover_music with audio_id and prompt="acoustic folk, gentle guitar"]

Available Models

Model

Tier

Description

FUZZ-2.0 Pro

Pro

Highest quality, best for professional production

FUZZ-2.0

Default

Recommended for most use cases (default)

FUZZ-2.0 Raw

Raw

Unprocessed output, for custom post-processing

FUZZ-1.1 Pro

Pro

High quality legacy model

FUZZ-1.0 Pro

Pro

Professional legacy model

FUZZ-1.0

Default

Stable legacy model

FUZZ-1.1

Default

Improved legacy model

FUZZ-0.8

Legacy

Original model, basic quality

Configuration

Environment Variables

Variable

Description

Default

ACEDATACLOUD_API_TOKEN

API token from AceDataCloud

Required

ACEDATACLOUD_API_BASE_URL

API base URL

https://api.acedata.cloud

ACEDATACLOUD_OAUTH_CLIENT_ID

OAuth client ID (hosted mode)

--

ACEDATACLOUD_PLATFORM_BASE_URL

Platform base URL

https://platform.acedata.cloud

PRODUCER_DEFAULT_MODEL

Default FUZZ model

FUZZ-2.0

PRODUCER_REQUEST_TIMEOUT

Request timeout in seconds

1800

LOG_LEVEL

Logging level

INFO

Command Line Options

mcp-producer --help

Options:
  --version          Show version
  --transport        Transport mode: stdio (default) or http
  --port             Port for HTTP transport (default: 8000)

Development

Setup Development Environment

# Clone repository
git clone https://github.com/AceDataCloud/ProducerMCP.git
cd ProducerMCP

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows

# Install with dev dependencies
pip install -e ".[dev,test]"

Run Tests

# Run unit tests
pytest

# Run with coverage
pytest --cov=core --cov=tools

# Run integration tests (requires API token)
pytest tests/test_integration.py -m integration

Code Quality

# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools

Build & Publish

# Install build dependencies
pip install -e ".[release]"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*

Project Structure

ProducerMCP/
├── core/                   # Core modules
│   ├── __init__.py
│   ├── client.py          # HTTP client for Producer API
│   ├── config.py          # Configuration management
│   ├── exceptions.py      # Custom exceptions
│   ├── oauth.py           # OAuth 2.1 provider
│   ├── server.py          # MCP server initialization
│   ├── types.py           # Type definitions (models, actions)
│   └── utils.py           # Utility functions
├── tools/                  # MCP tool definitions
│   ├── __init__.py
│   ├── audio_tools.py     # Audio generation tools (9 tools)
│   ├── lyrics_tools.py    # Lyrics generation
│   ├── media_tools.py     # Upload, video, WAV tools
│   ├── task_tools.py      # Task query tools
│   └── info_tools.py      # Information tools
├── prompts/                # MCP prompts
│   └── __init__.py        # Prompt templates
├── tests/                  # Test suite
│   ├── conftest.py
│   ├── test_client.py
│   ├── test_config.py
│   ├── test_integration.py
│   └── test_utils.py
├── deploy/                 # Deployment configs
│   └── production/
│       ├── deployment.yaml
│       ├── ingress.yaml
│       └── service.yaml
├── .env.example           # Environment template
├── .ruff.toml             # Ruff linter config
├── CHANGELOG.md
├── Dockerfile             # Docker image for HTTP mode
├── docker-compose.yaml    # Docker Compose config
├── LICENSE
├── main.py                # Entry point
├── pyproject.toml         # Project configuration
└── README.md

Contributing

Contributions are welcome! Please:

  1. Fork the repository

  2. Create a feature branch (git checkout -b feature/amazing)

  3. Commit your changes (git commit -m 'Add amazing feature')

  4. Push to the branch (git push origin feature/amazing)

  5. Open a Pull Request

Documentation

Documentation

License

MIT License - see LICENSE for details.


Made with love by AceDataCloud

Lyrics in extensions and replacements

producer_extend_music uses supplied lyric in custom mode. Lyrics are required unless instrumental=true; continue_at must be greater than zero. producer_replace_section also selects custom mode when lyric is supplied. Both operations preserve an explicit async=false and optional callback settings.

Available Tools

18 tools
producer_cover_musicAInspect

Create a cover or remix version of an existing song in a different style.

This generates a new version of a song with a different arrangement, genre,
or mood while keeping the core melody and lyrics.

Use this when:
- You want to hear a song in a different genre
- You want an acoustic/unplugged version of an electronic song
- You want to remix a song with a different vibe

Returns:
    Task ID and the cover audio information.

Inputs: audio_id (required), async, model, prompt, +1 more. Returns: result

producer_extend_musicAInspect

Extend an existing song from a specific timestamp with new content.

This allows you to continue a previously generated song, adding new sections
like additional verses, a bridge, or an outro.

Use this when:
- A generated song is too short and you want to add more
- You want to add a bridge or outro to an existing song
- You're building a longer song piece by piece

Returns:
    Task ID and the extended audio information.

Inputs: audio_id (required), continue_at (required), async, lyric, +4 more. Returns: result

producer_generate_custom_musicAInspect

Generate AI music with full control over lyrics, title, and style.

This gives you complete creative control over the song. You provide the lyrics
with section markers, and Producer generates the melody and arrangement.

Use this when:
- You have specific lyrics you want to use
- You want precise control over the music style
- You need a specific song title

For quick generation without writing lyrics, use producer_generate_music instead.

Returns:
    Task ID and generated audio information including URLs, title, lyrics, and duration.

Inputs: seed, async, lyric, model, +7 more. Returns: result

producer_generate_lyricsAInspect

Generate song lyrics from a text prompt.

Creates structured lyrics with proper song sections (Verse, Chorus, Bridge,
etc.) based on your description. The generated lyrics are formatted and
ready to use with producer_generate_custom_music.

Use this when:
- You need lyrics but don't want to write them yourself
- You want AI-generated lyrics for a specific theme or mood
- You need properly structured lyrics with section markers

The output includes section markers like [Verse], [Chorus], [Bridge] that
Producer's music generation understands.

Returns:
    Generated lyrics with title, status, and formatted text with section markers.

Inputs: prompt (required). Returns: result

producer_generate_musicAInspect

Generate AI music from a text prompt using Producer/Riffusion.

This is the simplest way to create music - just describe what you want and
Producer will automatically generate appropriate lyrics, melody, style, and
arrangement.

Use this when:
- You want quick music generation with minimal input
- You don't have specific lyrics in mind
- You want the AI to be creative with the arrangement

For full control over lyrics and style, use producer_generate_custom_music instead.

Returns:
    Task ID and generated audio information including URLs, title, lyrics, and duration.

Inputs: prompt (required), seed, async, model, +5 more. Returns: result

producer_generate_videoAInspect

Generate a video for a previously generated song.

Creates a video with visualizations for a generated audio track.
Useful for sharing on social media or video platforms.

Use this when:
- You want a video version of a generated song
- You need to share the song on video platforms
- You want a visual representation of the audio

Returns:
    Task ID and video generation information.

Inputs: audio_id (required). Returns: result

producer_generate_wavAInspect

Get the lossless WAV format of a generated song.

Converts the song to high-quality uncompressed WAV format.
WAV files are larger but have no quality loss compared to MP3.

Use this when:
- You need a lossless audio format for production
- You want the highest quality audio output
- You need uncompressed audio for further processing

Returns:
    Task ID and WAV audio information.

Inputs: audio_id (required). Returns: result

producer_get_lyric_format_guideAInspect

Get guidance on formatting lyrics for Producer music generation.

Shows how to structure lyrics with section markers for best results.
Following this format helps Producer understand the song structure and
generate appropriate melodies for each section.

Returns:
    Complete guide with section markers, examples, and tips.

Inputs: no named parameters. Returns: result

producer_get_taskAInspect

Query the status and result of a music generation task.

Use this to check if a generation is complete and retrieve the resulting
audio URLs, titles, lyrics, and other metadata.

Use this when:
- You want to check if a generation has completed
- You need to retrieve audio URLs from a previous generation
- You want to get the full details of a generated song

Task states:
- 'pending': Generation is still in progress — KEEP POLLING
- 'processing': Generation is being processed — KEEP POLLING
- 'complete': Generation finished successfully — this is the ONLY state that means done
- 'failed': Generation failed (check error message)

CRITICAL: During the 'pending' state, the response may already contain intermediate
audio_url values (streaming preview URLs). These are NOT final results. You MUST check
the 'state' field — only present the results to the user when state is 'complete' and
success is true. Do NOT stop polling just because audio_url is non-empty.

Returns:
    Task status and generated audio information including URLs, title, lyrics, and task timing metadata.

Inputs: task_id (required). Returns: result

producer_get_tasks_batchAInspect

Query multiple music generation tasks at once.

Efficiently check the status of multiple tasks in a single request.
More efficient than calling producer_get_task multiple times.

Use this when:
- You have multiple pending generations to check
- You want to get status of several songs at once
- You're tracking a batch of generations

CRITICAL: Same as producer_get_task — only consider a task complete when its state
is 'complete' and success is true. Intermediate audio_url values during 'pending'
state are streaming previews, NOT final results.

Returns:
    Status and audio information for all queried tasks.

Inputs: task_ids (required). Returns: result

producer_list_actionsAInspect

List all available Producer API actions and corresponding tools.

Reference guide for what each action does and which tool to use.
Helpful for understanding the full capabilities of the Producer MCP.

Returns:
    Categorized list of all actions and their corresponding tools.

Inputs: no named parameters. Returns: result

producer_list_modelsAInspect

List all available Producer/FUZZ models and their capabilities.

Shows all available model versions with their features and
recommended use cases. Use this to understand which model to choose
for your music generation.

Returns:
    Table of all models with their version and features.

Inputs: no named parameters. Returns: result

producer_replace_sectionAInspect

Replace a specific time range in a song with new generated content.

Re-generates a portion of a song between the specified start and end times,
keeping the rest of the song unchanged. Great for fixing sections you don't
like.

Use this when:
- A specific section of a song needs improvement
- You want to change lyrics in the middle of a song
- You want to replace a verse or chorus with something different

Returns:
    Task ID and the updated audio information.

Inputs: audio_id (required), replace_section_end (required), replace_section_start (required), async, +4 more. Returns: result

producer_stems_musicAInspect

Separate a song into individual stems (vocals and instruments).

Splits the audio into separate tracks for vocals and instrumentals,
useful for remixing, karaoke, or isolating specific parts.

Use this when:
- You want to separate vocals from instrumentals
- You need individual stem tracks for mixing
- You want to create a karaoke version

Returns:
    Task ID and stem separation results with individual track URLs.

Inputs: audio_id (required), async, callback_url. Returns: result

producer_swap_instrumentalsAInspect

Swap the instrumental track of one song with instrumentals from another.

Requests instrumental swapping for the provided audio.

Use this when:
- You want to combine instrumentals from one song with vocals from another
- You want to hear how the same vocals sound over different music
- You're creating an instrumental mashup

Returns:
    Task ID and the swapped audio information.

Inputs: audio_id (required), async, callback_url. Returns: result

producer_swap_vocalsAInspect

Swap the vocals of one song with vocals from another song.

Requests vocal swapping for the provided audio.

Use this when:
- You want to combine vocals from one song with instrumentals from another
- You want to hear how different vocals sound over the same beat
- You're creating a vocal mashup

Returns:
    Task ID and the swapped audio information.

Inputs: audio_id (required), async, callback_url. Returns: result

producer_upload_audioAInspect

Upload an external audio file for use in subsequent operations.

Uploads audio from a URL so it can be used with actions like extend,
cover, variation, swap_vocals, and swap_instrumentals.

Use this when:
- You have your own music you want to process with Producer
- You want to use an external audio as a base for operations
- You need to import audio into Producer's system

After uploading, use the returned audio_id with other Producer tools.

Returns:
    Upload result with audio ID for use in subsequent operations.

Inputs: audio_url (required). Returns: result

producer_variation_musicAInspect

Create a variation of an existing song with modifications.

Generates a new version of the song with subtle changes to the arrangement,
melody, or style while keeping the overall structure similar.

Use this when:
- You like a song but want a slightly different version
- You want to explore different interpretations of the same idea
- You need multiple takes of a similar song

Returns:
    Task ID and the variation audio information.

Inputs: audio_id (required), async, model, prompt, +1 more. Returns: result

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 18 tools

    Disambiguation4/5

    Most tools map to a clearly distinct operation (generate vs extend vs cover vs variation vs swap_vocals vs swap_instrumentals vs replace_section vs stems), and the two generation tools explicitly cross-reference each other to disambiguate. The only soft overlap is cover_music versus variation_music, which differ mainly in degree of stylistic change rather than in mechanism.

    Naming Consistency4/5

    All tools carry a uniform producer_ prefix and snake_case verb_noun style, with a shared _music suffix on the audio-mutating operations. Minor deviations appear in noun-first names like stems_music and variation_music, and get_tasks_batch is pluralized differently from get_task, but the pattern is still highly predictable.

    Tool Count4/5

    Eighteen tools is on the heavy side but justifiable given the breadth of a music-generation platform (six distinct audio transforms plus generation, lyrics, upload, WAV, video, and task polling). A few slots are spent on reference-only helpers (list_actions, lyric format guide, list_models), which are useful for discoverability but inflate the count.

    Completeness4/5

    The surface covers the full generation lifecycle: prompt or lyric-driven creation, lyric generation and formatting guidance, extend/cover/variation/replace, vocal and instrumental swaps, stem separation, WAV export, video rendering, external upload, and both single and batch task polling. Gaps remain around async job management (no cancel or delete task, no list/history of prior songs) and no way to merge extended segments into one continuous track.

    Maintenance

    ActivityActive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers