io.github.jmedure/talkback MCP Server
io.github.jmedure/talkback
Chat with your Ableton Live session in real-time using natural language through Claude or Cursor.
What is the io.github.jmedure/talkback MCP server?
The talkback MCP server connects AI assistants like Claude to Ableton Live, enabling real-time conversation about your music production. It reads tracks, adjusts parameters, analyzes mixes, and captures spectral data through a Max for Live bridge that streams session data over WebSocket.
Talkback lets you interact with your Ableton Live session conversationally—ask an AI to analyze your mix, adjust EQ, fix muddy bass, or explain what's happening in your tracks. It bridges Ableton's Live Object Model to Claude Desktop, Cursor, or other MCP clients, giving AI assistants real-time read and write access to your session with approval gates for parameter changes.
How to install io.github.jmedure/talkback
Copy-paste configuration for popular MCP clients.
WS_PORTWebSocket port for the Max for Live bridge connection
Tools & capabilities
Tools this server exposes to the agent.
get_session_context— Reads your full session including tracks, volumes, panning, mutes, sends, devices, and routingget_track_details— Deep-dives a single track with every device parameter in human-readable unitsget_spectral_snapshot— Captures ~2s of live audio from master bus with peak/RMS per frequency bandget_plugin_library— Lists all installed AU and VST3 plugins on your systemanalyze_mix— Runs heuristic checks for frequency buildup, dynamics, headroom, and routing issuesset_device_parameter— Changes a device parameter using human-readable units (dB, ms, Hz, etc.)toggle_device_bypass— Enables or bypasses a device for A/B comparisoncreate_group_track— Creates a new group track containing specified tracksset_track_routing— Changes a track's output routing to another track or busget_bridge_health— Returns bridge performance metrics from the M4L device
Use cases
- Ask an AI to analyze your mix for frequency buildup, dynamics issues, and headroom problems
- Get real-time help fixing muddy bass or other mix problems by describing what you hear
- Adjust EQ, compression, and other device parameters via natural language conversation
- Perform A/B comparisons by toggling devices on and off through chat
- Understand your session structure and routing by asking the AI to explain what's connected where
io.github.jmedure/talkback MCP server FAQ
Talkback is an MCP server that connects AI assistants (Claude, Cursor, etc.) to Ableton Live in real-time. It lets you chat about your music production—analyze mixes, adjust parameters, and get spectral feedback—all through conversation.
Yes, talkback is free to use, modify, and distribute under the PolyForm Shield 1.0.0 license.
Download Claude Desktop, then add talkback-mcp to your claude_desktop_config.json file with the provided configuration. The fastest way is to run the install script: curl -fsSL https://talkback.createwcare.com/install.sh | bash
Yes, you need Ableton Live 11+ with Max for Live. You must install the talkback-bridge Max for Live device on your master track for the MCP server to connect.
Ableton Live 11+, Max for Live, Node.js 18+, and a desktop MCP client like Claude Desktop, Claude Code, or Cursor. Talkback does not work with claude.ai in the browser.
No, the AI asks for approval before making any parameter changes. Undo always works if you want to revert changes.
README (reference)
Source of truth, from the repository.
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.
- talkback bridge — a Max for Live device on your master track that reads the Live Object Model and streams session data over WebSocket
- 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:
curl -fsSL https://talkback.createwcare.com/install.sh | bash
Already in an AI agent? Let it set things up for you:
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).
<details> <summary><b>Claude Desktop</b> (recommended)</summary>Download Claude Desktop, then add to your config:
~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
%APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"talkback-mcp": {
"command": "npx",
"args": ["-y", "talkback-mcp"],
"env": { "WS_PORT": "8765" }
}
}
}
Restart Claude Desktop after saving.
</details> <details> <summary>Claude Code</summary>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
npxinstead — runwhich npxin Terminal, then set that as"command"in the config above. See troubleshooting for details.
claude mcp add --transport stdio talkback-mcp -- npx -y talkback-mcp
</details>
<details>
<summary>Cursor</summary>
Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"talkback-mcp": {
"command": "npx",
"args": ["-y", "talkback-mcp"],
"env": { "WS_PORT": "8765" }
}
}
}
</details>
<details>
<summary>Other clients (Windsurf, etc.)</summary>
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:
npx add-mcp "npx -y talkback-mcp"
</details>
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
| Tool | What it does |
|---|---|
get_session_context | Reads your full session — tracks, volumes, panning, mutes, sends, devices, routing |
get_track_details | Deep-dives a single track with every device parameter in human-readable units |
get_spectral_snapshot | Captures ~2s of live audio from master bus with peak/RMS per frequency band |
get_plugin_library | Lists all installed AU and VST3 plugins on your system |
analyze_mix | Runs heuristic checks for frequency buildup, dynamics, headroom, and routing issues |
set_device_parameter | Changes a device parameter using human-readable units (dB, ms, Hz, etc.) |
toggle_device_bypass | Enables or bypasses a device for A/B comparison |
create_group_track | Creates a new group track containing specified tracks |
set_track_routing | Changes a track's output routing to another track or bus |
get_bridge_health | Returns 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
| Variable | Default | Description |
|---|---|---|
WS_PORT | 8765 | WebSocket 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.
Related MCP servers

Privacy-safe synthetic financial data for LatAm fintech, AI agents, testing and ML.
Persistent knowledge graph MCP server for neurodivergent thinking patterns with BM25 search and no cloud dependency.

Font Lab
A decision surface for typography: curate font directions on your real site, ship next/font code.

Memoria personal para Claude Code en notas Markdown; no carga el contexto a ciegas.

GitLab MCP Server
AI-native GitLab client: 1000+ REST/GraphQL actions in plain language for merge requests, pipelines, issues, and releases.
Markdown to styled HTML, PDF, DOCX, and slides with themes, diagrams, and math.
View repository →
