Lacuna MCP

by JOYLINK-LTD

281 downloads
Not rated
GitHub

About

Model Context Protocol server for the Lacuna Music API — generate AI music from Claude Desktop, Claude Code, Cursor, Zed, and other MCP-compatible clients.

Details

Author
JOYLINK-LTD
Downloads
281
Categories
Developer Tools, AI

- Create music generation tasks and get immediate pending task IDs.
- Retrieve the current state of a generation task by its ID.
- Poll a generation task until it completes or fails.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Lacuna MCP
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

The server is a single npm package run over stdio. No install step is needed — your MCP client launches it via npx lacuna-mcp. Configure it by setting the LACUNA_API_KEY environment variable (required, from your profile dashboard, begins with lyr_live_). An optional LACUNA_BASE_URL can override the API base URL. Music API access requires the Pro plan or above.

generate_music

Create an AI music generation task on Lacuna. Returns immediately with a `pending` task; use `wait_for_generation` or `get_generation` to retrieve the finished tracks.

get_generation

Retrieve the current state of a music generation task by id.

wait_for_generation

Poll a generation task until it reaches a terminal state (`ready` or `failed`) or the timeout elapses. Returns the final task object including audio URLs on success.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "lacuna mcp": {
            "lacuna": {
                "command": "npx",
                "args": [
                    "-y",
                    "lacuna-mcp"
                ],
                "env": {
                    "LACUNA_API_KEY": "lyr_live_..."
                }
            }
        }
    }
}

McpServers

{
    "lacuna": {
        "command": "npx",
        "args": [
            "-y",
            "lacuna-mcp"
        ],
        "env": {
            "LACUNA_API_KEY": "lyr_live_..."
        }
    }
}

lacuna-mcp

Model Context Protocol server for the Lacuna Music API. Lets MCP-compatible clients (Claude Desktop, Claude Code, Cursor, Zed, Continue, etc.) generate AI music as part of an agent loop.

Installation

The server is published as a single npm package and runs over stdio. No install step is needed — your MCP client launches it via npx. ``sh npx lacuna-mcp `

Configuration

| Variable | Required | Description | | ------------------ | -------- | --------------------------------------------------------------------------- | |
LACUNA_API_KEY | yes | API key from your profile dashboard. Begins with lyr_live_. | | LACUNA_BASE_URL | no | Override the API base URL (e.g. for staging). | Music API access requires the Pro plan or above.

Claude Desktop

`json { "mcpServers": { "lacuna": { "command": "npx", "args": ["-y", "lacuna-mcp"], "env": { "LACUNA_API_KEY": "lyr_live_..." } } } } `

Claude Code

`sh claude mcp add lacuna -- npx -y lacuna-mcp `

Tools

| Tool | Description | | ------------------------- | ---------------------------------------------------------------------------------------------------- | |
generate_music | Create a music generation task. Returns a pending task immediately. | | get_generation | Retrieve the current state of a generation task by id. | | wait_for_generation | Poll a task until it reaches a terminal state (ready or failed`) or the timeout elapses. |

Requirements

- Node.js 18 or newer. - An API key from a Lacuna Pro plan or above.

License

MIT © Louis Tsang
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.