Talkback

io.github.jmedure由 GitHub 帳號 jmedure 發布v0.1.3更新於 Oct 24, 2026

Chat with your Ableton session in real-time.

已驗證STDIO僅桌面開發者工具媒體與設計

概覽

AI 產生的概覽

把 AI 助理連接到正在運作的 Ableton Live 專案，可讀取軌道、調整裝置參數並分析混音的 MCP 伺服器。

可以做什麼
  • 讀取專案：完整軌道清單及音量、聲像、靜音、送出、裝置與路由，並可深入查看單一軌道的所有裝置參數
  • 分析混音：檢查頻段堆積、動態、餘裕與路由問題的啟發式分析，以及主總線的短時頻譜快照
  • 修改專案：以 dB、ms、Hz 等可讀單位設定裝置參數、旁通裝置做 A/B 比較、建立編組軌道、變更軌道輸出路由
  • 檢視環境：列出系統已安裝的 AU 與 VST3 外掛，並回傳橋接裝置的效能指標
適用情境
適合在 Ableton Live 中製作音樂、希望透過對話了解專案狀況、取得混音建議或直接調整參數而不必逐一開啟裝置的使用者。
執行需求
以 npm 套件形式透過 npx 在本機執行，需要 Node.js 18+ 與桌面版 MCP 用戶端（如 Claude Desktop、Claude Code、Cursor，瀏覽器聊天不支援）。需要 Ableton Live 11+ 與 Max for Live，並在主軌道上放置並啟用 talkback 橋接裝置。環境變數 WS_PORT 指定 WebSocket 連接埠（預設 8765）。
安裝前請注意
此伺服器會變更專案：設定裝置參數、旁通裝置、建立編組軌道與變更路由，核准前應確認變更內容。它會讀取完整專案狀態與外掛清單，並從主總線擷取即時音訊。README 的快速安裝會執行從網路取得的 shell 腳本，執行前應先檢查腳本內容。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Talkback，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。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

talkback mcp

Chat with your Ableton session in natural language. Go deeper in your mix, make it sound like it does in your head, and finally understand compression... jk no one can teach you that.

Talkback is an MCP server and Max for Live device that gives AI assistants real-time access to your Ableton Live session — read tracks, adjust parameters, analyze your mix, and get spectral snapshots, all through conversation.

talkback.createwcare.com  ·  Docs  ·  Changelog

How it works

Ableton Live ↔ M4L Bridge ↔ WebSocket ↔ MCP Server ↔ Claude / Cursor / etc.
  1. talkback bridge — a Max for Live device on your master track that reads the Live Object Model and streams session data over WebSocket
  2. talkback-mcp (this package) — an MCP server that exposes your session as tools any LLM can use

Quick start

The fastest way to get set up — installs the MCP server and configures Claude Desktop automatically:

bash
curl -fsSL https://talkback.createwcare.com/install.sh | bash

Already in an AI agent? Let it set things up for you:

bash
npx skills add jmedure/talkback-mcp

Then ask your agent: "Help me set up talkback"

Requires Node.js 18+. See the full setup guide for more options.

1. Install the Max for Live device

Download talkback-bridge (latest) and drop it onto your master track in Ableton. Make sure the device is toggled on.

2. Add the MCP server

Talkback requires a desktop MCP client — it runs locally on your machine and connects to Ableton over WebSocket. It does not work with claude.ai in the browser (web chat doesn't support local MCP servers yet).

Claude Desktop (recommended)

Download Claude Desktop, then add to your config:

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) %APPDATA%\Claude\claude_desktop_config.json (Windows)

json
{  "mcpServers": {    "talkback-mcp": {      "command": "npx",      "args": ["-y", "talkback-mcp"],      "env": { "WS_PORT": "8765" }    }  }}

Restart Claude Desktop after saving.

Using nvm or fnm? Claude Desktop doesn't load your shell profile, so it may pick up an old system Node. Use the full path to npx instead — run which npx in Terminal, then set that as "command" in the config above. See troubleshooting for details.

Claude Code
bash
claude mcp add --transport stdio talkback-mcp -- npx -y talkback-mcp
Cursor

Add to .cursor/mcp.json in your project root:

json
{  "mcpServers": {    "talkback-mcp": {      "command": "npx",      "args": ["-y", "talkback-mcp"],      "env": { "WS_PORT": "8765" }    }  }}
Other clients (Windsurf, etc.)

Point your client at npx -y talkback-mcp as the server command with WS_PORT=8765 as an environment variable.

Or use add-mcp to auto-configure all your installed agents:

bash
npx add-mcp "npx -y talkback-mcp"

3. Start chatting

Open your LLM and start asking about your session:

  • "What's going on in my session?"
  • "My bass sounds muddy, can you help?"
  • "Cut 3 dB at 300 Hz on the vocal EQ"
  • "Does my mix have any obvious problems?"

Your LLM will ask for approval before making any parameter changes. Undo always works.

Tools

ToolWhat it does
get_session_contextReads your full session — tracks, volumes, panning, mutes, sends, devices, routing
get_track_detailsDeep-dives a single track with every device parameter in human-readable units
get_spectral_snapshotCaptures ~2s of live audio from master bus with peak/RMS per frequency band
get_plugin_libraryLists all installed AU and VST3 plugins on your system
analyze_mixRuns heuristic checks for frequency buildup, dynamics, headroom, and routing issues
set_device_parameterChanges a device parameter using human-readable units (dB, ms, Hz, etc.)
toggle_device_bypassEnables or bypasses a device for A/B comparison
create_group_trackCreates a new group track containing specified tracks
set_track_routingChanges a track's output routing to another track or bus
get_bridge_healthReturns bridge performance metrics from the M4L device

Requirements

  • Ableton Live 11+ with Max for Live
  • Node.js 18+
  • A desktop MCP client — Claude Desktop (recommended), Claude Code, Cursor, or similar

Environment variables

VariableDefaultDescription
WS_PORT8765WebSocket port for bridge connection

License

PolyForm Shield 1.0.0 — free to use, modify, and distribute. You may not use this software to build a competing product.

來源：README.md，提交 0db664d

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包，因此其工具未知。

版本歷史

1
  1. v0.1.3最新Sep 16, 2026

評分

已滿足適用檢查項的 40%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手；SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭，或保持端點能夠回應探測，以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。