MCP MeasureMCP Measure

索引已观测

Lacuna Music

Generate AI music via the Lacuna Music API from MCP clients like Claude Desktop & Code.

我该使用它吗

质量与安全性

A
描述质量
100%
模式完整度
77%
命名质量
100%
投毒风险
100%
权限匹配度
100%
协议合规性
100%

基于对工具定义和协议合规性的自动分析。

上下文开销

~542token 数（工具定义）
~1.4 KB典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.42%）

这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。

安装

一键安装

将以下内容添加到你的 `claude_desktop_config.json` 文件中：

{
  "mcpServers": {
    "lacuna-mcp": {
      "command": "npx",
      "args": [
        "lacuna-mcp"
      ]
    }
  }
}

可运行的软件包

npmlacuna-mcp0.3.4stdio

远程端点

https://www.lacuna.fm/mcpstreamable-http

它能做什么

工具清单

工具（3）

🟢 只读🟡 写入🔴 删除⚪ 未知
🟡generate_music(style, title, lyrics, instrumental, model, ...)

Create an AI music generation task on Lacuna. Returns immediately with a `pending` task; poll `get_generation` to retrieve the finished tracks and their audio URLs.

输入模式

{
  "type": "object",
  "properties": {
    "style": {
      "type": "string",
      "maxLength": 1000,
      "description": "Style description, e.g. \"pop, female vocal, 120 bpm, energetic\"."
    },
    "title": {
      "type": "string",
      "maxLength": 200,
      "description": "Track title."
    },
    "lyrics": {
      "type": "string",
      "maxLength": 5000,
      "description": "Lyrics in plain text. Required unless `instrumental` is true."
    },
    "instrumental": {
      "type": "boolean",
      "description": "Generate an instrumental track (no lyrics). Defaults to false."
    },
    "model": {
      "type": "string",
      "enum": [
        "aether",
        "echo"
      ],
      "description": "Generation model. Defaults to `aether`. Call `list_models` for what each one covers."
    },
    "vocal_gender": {
      "type": "string",
      "enum": [
        "m",
        "f"
      ],
      "description": "Lead vocal gender hint (aether only)."
    },
    "negative_tags": {
      "type": "string",
      "maxLength": 500,
      "description": "Negative style tags to avoid (aether only)."
    },
    "style_weight": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "description": "Style weight 0–1 (aether only)."
    },
    "weirdness_constraint": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "description": "Weirdness constraint 0–1 (aether only)."
    },
    "audio_weight": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "description": "Audio reference weight 0–1 (aether only)."
    }
  },
  "required": [
    "style",
    "title"
  ],
  "additionalProperties": false
}
🟢get_generation(id)

Retrieve the current state of a music generation task by id. Status is `pending`, `ready`, or `failed`; audio URLs appear on `ready`.

输入模式

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Generation task id, returned by generate_music."
    }
  },
  "required": [
    "id"
  ],
  "additionalProperties": false
}
🟢list_models

List the music models available through the API, with their credit cost per task, tracks produced per task, and language coverage.

输入模式

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

社区

评价此服务器

证据

最近观测

已验证未记录版本3 个工具
已验证未记录版本3 个工具
已验证未记录版本3 个工具