Tuney

io.github.library-xv1.0.0更新於 Oct 10, 2026

Royalty-free music fitted to your length: find, generate, adjust and download tracks and stems.

已驗證Streamable HTTP可網頁執行Media & DesignProductivity & Workflow

概覽

AI 產生的概覽

讓助理尋找、生成、調整並下載依精確長度裁切的免權利金音樂曲目與分軌。

功能
Tuney 提供列出風格、尋找現成曲目、以手工製作的音樂元素依指定長度生成新曲目,以及追蹤生成或下載工作的工具。它能顯示曲目詳細資料,依新的長度、轉折點、結尾、速度或調性重新算繪曲目,靜音或重新生成分軌,並回傳 mp3、wav 或分軌的下載連結。它也會顯示所連接的帳號及其點數餘額。
適用情境
當你需要為影片、廣告、播客、遊戲或應用程式準備免權利金背景音樂,並希望助理搜尋、創作並把音樂調整到精確長度時,它很有用。如果你已經在聊天或程式開發用戶端中工作,並希望在同一段對話裡完成音樂挑選與編輯,值得加入。
執行需求
這是透過 streamable HTTP 存取的遠端 MCP 伺服器,使用文件提供的伺服器網址,不需要本機套件或執行環境。它需要 Tuney 帳號,並在瀏覽器中透過 OAuth 2.0 登入(授權碼加 PKCE、動態用戶端註冊);不支援需要預先註冊用戶端 ID 或靜態權杖的用戶端。需要能連線到 Tuney API 的網路。
安裝前請注意
下載最終檔案會像在 Tuney 應用程式中一樣消耗帳號點數;搜尋、生成、調整與試聽是免費的。登入使用 OAuth,伺服器不會看到你的密碼,在用戶端中斷連線會撤銷它對帳號的存取。你建立的曲目會保留在帳號中,隱私權聲明說明了伺服器儲存的內容。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Tuney,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "tuney": {
      "type": "http",
      "url": "https://api.tuney.io/cue-engine2/connector/mcp"
    }
  }
}

README

Tuney MCP server

Tuney is royalty-free music for video, ads, podcasts, games and apps, built from musical elements composed, performed and recorded by musicians and fitted to the exact length you need. This repository is the home of the Tuney MCP server: one remote server that any MCP client can use, and install instructions for the assistants and editors people ask about most.

  • Server URL: https://api.tuney.io/cue-engine2/connector/mcp
  • Transport: MCP streamable HTTP
  • Authentication: OAuth 2.0 (authorization code with PKCE, dynamic client registration). You sign in with your Tuney account in the browser; the server never sees your password.
  • Account: a Tuney account, free to create at app.tuney.io. Searching, generating, adjusting and listening to previews is free. Downloading a final file uses the credits of your account, exactly as in the Tuney app.
  • Documentation: app.tuney.io/claude · Privacy notice: app.tuney.io/claude/privacy · Support: [email protected]

What the server can do

ToolWhat it doesUses credits
list_stylesLists the genres, moods and tempos Tuney works withno
find_tracksFinds ready-made tracks for a brief, or by genre, mood and tempo, with instant previewsno
generate_trackComposes a new track from Tuney's hand-made elements, fitted to an exact length (5 s to 10 min)no
get_task / wait_for_taskFollows a generation or download until it is doneno
get_trackShows a track: name, preview link, length, bpm, key, style and sectionsno
adjust_trackRe-renders a track with a new length, a turning point, a fade-out or short ending, a tempo or key change, stems muted or regeneratedno
download_trackGives a download link for the final file as mp3, wav or stems (melody, chords, bass, drums, effects)yes
get_accountShows which Tuney account is connected and its credit balanceno

You never call the tools yourself. Ask your assistant for what you need, for example:

  • "Find me a warm acoustic track for a 45 second travel vlog intro."
  • "Generate an upbeat 30 second pop track for a product video."
  • "Make it 60 seconds with a turning point at 30 and a short ending."
  • "Drop the drums for the voice-over part."
  • "Download it as stems."

Connect from your client

Claude (claude.ai, Claude Desktop, Claude mobile)

Settings → Connectors → Add custom connector, paste the server URL, then Connect and sign in with your Tuney account. Once Tuney is listed in the Claude connector directory you can also add it from there with one click.

Claude Code

Install the Tuney plugin, which adds the server together with a skill that teaches Claude how to use it well:

bash
claude plugin marketplace add library-x/tuney_claude_pluginclaude plugin install tuney@tuney

Or add just the server:

bash
claude mcp add --transport http tuney https://api.tuney.io/cue-engine2/connector/mcp

Then run /mcp inside Claude Code and sign in in the browser window that opens. Plugin source: library-x/tuney_claude_plugin.

ChatGPT

ChatGPT connects to MCP servers through developer mode:

  1. Settings → Connectors → Advanced → turn on Developer mode.
  2. Back in Connectors, choose Create, give it the name Tuney, paste the server URL, set Authentication to OAuth, and create it.
  3. Sign in with your Tuney account when asked.
  4. In a chat, open the tools menu ("+" or More) and enable Tuney.

Developer mode is available on paid ChatGPT plans. On Team, Enterprise and Edu plans an admin may need to enable it first.

Cursor

Click to install:

[Install in Cursor]

Or add it to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project):

json
{  "mcpServers": {    "tuney": {      "url": "https://api.tuney.io/cue-engine2/connector/mcp"    }  }}

Cursor detects that the server uses OAuth and shows a Sign in action next to it in Settings → MCP.

VS Code (GitHub Copilot)

Add it from the command line:

bash
code --add-mcp '{"name":"tuney","type":"http","url":"https://api.tuney.io/cue-engine2/connector/mcp"}'

Or put this in .vscode/mcp.json in your workspace (or in your user profile's mcp.json):

json
{  "servers": {    "tuney": {      "type": "http",      "url": "https://api.tuney.io/cue-engine2/connector/mcp"    }  }}

Start the server from the MCP view or the MCP: List Servers command; VS Code opens the Tuney sign-in page the first time.

Codex CLI

bash
codex mcp add tuney --url https://api.tuney.io/cue-engine2/connector/mcpcodex mcp login tuney

codex mcp list shows the server and whether you are signed in. The same entry can be written by hand in ~/.codex/config.toml:

toml
[mcp_servers.tuney]url = "https://api.tuney.io/cue-engine2/connector/mcp"

Gemini CLI

bash
gemini mcp add --transport http tuney https://api.tuney.io/cue-engine2/connector/mcp

Then, inside Gemini CLI, run /mcp auth tuney to sign in. The equivalent entry in ~/.gemini/settings.json:

json
{  "mcpServers": {    "tuney": {      "httpUrl": "https://api.tuney.io/cue-engine2/connector/mcp",      "oauth": { "enabled": true }    }  }}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

json
{  "mcpServers": {    "tuney": {      "serverUrl": "https://api.tuney.io/cue-engine2/connector/mcp"    }  }}

Any other MCP client

Use the server URL with the streamable HTTP transport. The server follows the MCP authorization specification, so a client that supports OAuth 2.0 with dynamic client registration needs nothing else. For implementers, discovery lives at:

  • Protected resource metadata: https://api.tuney.io/cue-engine2/connector/.well-known/oauth-protected-resource
  • Authorization server metadata: https://api.tuney.io/cue-engine2/connector/.well-known/oauth-authorization-server
  • Host-root copies of both, for clients that look there: https://api.tuney.io/.well-known/oauth-authorization-server/cue-engine2/connector and https://api.tuney.io/.well-known/oauth-protected-resource/cue-engine2/connector/mcp

Clients that need a pre-registered client ID or a static token are not supported; registration is dynamic and open.

MCP Registry

The server is published in the official MCP Registry as io.github.library-x/tuney; server.json in this repository is the listing source.

Disconnecting and data

Disconnecting in your client revokes its access to your Tuney account; tracks you created stay in your account. The privacy notice describes what the server stores (short-lived sessions and tokens) and what it does not (your conversations). Questions: [email protected].

License

The contents of this repository are MIT licensed. Music from Tuney is licensed under the Tuney terms.

來源:README.md,提交 4e62d33

工具

0
工具後設資料尚未被收錄。

版本歷史

1
  1. v1.0.0最新Oct 10, 2026