ProducerMCP
by AceDataCloud
README.md
# ProducerMCP
<!-- mcp-name: io.github.AceDataCloud/mcp-producer -->
[](https://pypi.org/project/mcp-producer/)
[](https://pypi.org/project/mcp-producer/)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
[](https://modelcontextprotocol.io)
A [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server for AI music generation using [Producer/Riffusion](https://www.riffusion.com/) (FUZZ models) through the [AceDataCloud API](https://platform.acedata.cloud?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=producer_mcp_readme_platform).
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
## 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](https://platform.acedata.cloud/documents/producer?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=producer_mcp_readme_quick_start) 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](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp).
- **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](https://code.claude.com/docs/en/mcp).
- **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](https://cursor.com/docs/mcp).
- **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](https://code.visualstudio.com/docs/agent-customization/mcp-servers).
- **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](https://developers.openai.com/codex/mcp/).
Cursor project config (OAuth):
```json
{
"mcpServers": {
"producer": {"url": "https://producer.mcp.acedata.cloud/mcp"}
}
}
```
VS Code-specific workspace config (OAuth):
```json
{
"servers": {
"producer": {"type": "http", "url": "https://producer.mcp.acedata.cloud/mcp"}
}
}
```
### Hosted API token
<!-- BEGIN TOKEN ONBOARDING -->
1. Open [Ace Data Cloud → Applications](https://platform.acedata.cloud/console/applications?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=producer_mcp_readme_api_key). 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](https://platform.acedata.cloud/models?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=producer_mcp_readme_models).
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.
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.
<!-- END TOKEN ONBOARDING -->
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:
```bash
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:
```json
{
"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:
```json
{
"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:
```json
{
"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](https://docs.cline.bot/mcp/mcp-overview) · [JetBrains](https://www.jetbrains.com/help/ai-assistant/mcp.html) · [Zed](https://zed.dev/docs/ai/mcp).
### Local stdio
Install the package and give the local process an API token:
```bash
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](https://docs.astral.sh/uv/) on `PATH`:
```json
{
"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](https://platform.acedata.cloud/documents/producer?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=producer_mcp_readme_quick_start) 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 |
## 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
```bash
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
```bash
# 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
```bash
# 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
```bash
# Format code
ruff format .
# Lint code
ruff check .
# Type check
mypy core tools
```
### Build & Publish
```bash
# 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
<!-- canonical-documentation -->
[Documentation](https://platform.acedata.cloud/documents/producer?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=producer_mcp_readme_quick_start)
## License
MIT License - see [LICENSE](LICENSE) for details.
## Links
- [AceDataCloud Platform](https://platform.acedata.cloud?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=producer_mcp_readme_platform)
- [Riffusion](https://www.riffusion.com/)
- [Model Context Protocol](https://modelcontextprotocol.io)
- [MCP Python SDK](https://github.com/modelcontextprotocol/python-sdk)
---
Made with love by [AceDataCloud](https://platform.acedata.cloud?utm_source=github&utm_medium=referral&utm_campaign=evergreen&utm_content=producer_mcp_readme_platform)
TDQS
A3.9/5.0
Scored across 18 tools
Disambiguation4/5
Most tools cleanly separate generation, modification, retrieval, and audio processing concerns. The main ambiguity is between cover_music and variation_music, both of which create alternative versions of an existing song, though their descriptions distinguish genre/remix changes from subtle arrangement variations. get_task and get_tasks_batch are also adjacent but clearly differentiated by single vs. batch polling.
Naming Consistency4/5
All tools share the producer_ prefix and mostly follow a verb_noun pattern such as generate_music, get_task, swap_vocals, and upload_audio. A few names like variation_music and stems_music break the verb-first pattern, and get_lyric_format_guide uses a longer compound object, so consistency is good but not perfect.
Tool Count4/5
18 tools is above the typical 3-15 range, but the music production workflow justifies most of them: generation, editing, stems, swaps, video, lyrics, upload, and task polling. The two reference guides and the separate single/batch task query tools add mild bulk, but no tool feels truly extraneous.
Completeness4/5
The domain is covered end-to-end: create music via prompt or lyrics, retrieve results, modify via extend/cover/variation/replace, process via stems/swaps/WAV/video, and import external audio. Minor conveniences like listing all tasks or cancelling a task are absent, but core workflows have no dead ends.
Maintenance
ActivityActive
ResponsivenessUnresponsive