talkback-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@talkback-mcp Analyze my mix for frequency buildup"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: io.github.peterkolbe/ableton-for-ai
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 | bashAlready in an AI agent? Let it set things up for you:
npx skills add jmedure/talkback-mcpThen 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).
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.
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-mcpAdd to .cursor/mcp.json in your project root:
{
"mcpServers": {
"talkback-mcp": {
"command": "npx",
"args": ["-y", "talkback-mcp"],
"env": { "WS_PORT": "8765" }
}
}
}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"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 |
| Reads your full session — tracks, volumes, panning, mutes, sends, devices, routing |
| Deep-dives a single track with every device parameter in human-readable units |
| Captures ~2s of live audio from master bus with peak/RMS per frequency band |
| Lists all installed AU and VST3 plugins on your system |
| Runs heuristic checks for frequency buildup, dynamics, headroom, and routing issues |
| Changes a device parameter using human-readable units (dB, ms, Hz, etc.) |
| Enables or bypasses a device for A/B comparison |
| Creates a new group track containing specified tracks |
| Changes a track's output routing to another track or bus |
| 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 |
|
| 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.
Available Tools
10 toolsanalyze_mixA
Runs rule-based heuristic analysis for potential mix issues: frequency buildup, dynamics problems, routing inefficiencies, headroom. Only call when the user explicitly asks for mix feedback or describes a specific problem — do NOT call proactively. Findings are suggestions to consider, not problems to fix. Mix quality is subjective — frame results in context of what the user is trying to achieve. A technically 'imperfect' setting may be an intentional artistic choice.
Inputs: no named parameters.
create_group_trackA
Creates a new group track containing the specified tracks. Always confirm with the producer first.
Inputs: group_name (required), track_names (required).
get_bridge_healthA
Returns performance metrics from the M4L bridge device: poll execution time (avg/max), WebSocket message size, LiveAPI cache size, and track count. Use to diagnose performance issues or confirm the device is running efficiently.
Inputs: no named parameters.
get_plugin_libraryA
Returns all audio plugins (AU, VST3) installed on this system. Use to know what tools the producer has available.
Inputs: filter.
get_session_contextA
Returns a snapshot of the current Ableton session: all tracks (names, volumes, panning, mutes, sends, device chains), return tracks, master track, and routing. Call once at the start of a conversation to orient yourself. No need to call again unless the user says the session has changed.
Inputs: no named parameters.
get_spectral_snapshotA
Captures ~2 seconds of live audio from the master bus and returns peak/RMS levels across frequency bands. Transport MUST be playing — coordinate with the user on which section to analyze (e.g., 'play the chorus'). This is a point-in-time microscope, not a full-song analyzer. Use as a secondary check to verify what device parameter analysis suggests, or to detect issues invisible in the device chain (masking, phase, resonances). For most frequency questions, reading EQ and filter parameters via get_track_details is more informative.
Inputs: source.
get_track_detailsA
Returns full detail for a specific track including all devices, every parameter in human-readable units, and per-device observations.
Inputs: track_name (required).
set_device_parameterA
Sets a device parameter to a new value. Pass values in human-readable units (dB, ms, Hz, ratio, percent). NEVER call without explicit user approval. Present the planned change with current → proposed values first, wait for a clear 'yes', then execute. If the user modifies the plan, re-present and re-confirm before executing.
Inputs: unit (required), value (required), track_name (required), device_name (required), +1 more.
set_track_routingB
Changes a track's output routing. Always confirm with the producer first.
Inputs: track_name (required), output_target (required).
toggle_device_bypassA
Enables or bypasses a device on a track. Useful for A/B comparison. Always confirm with the user before toggling.
Inputs: active (required), track_name (required), device_name (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 10 tools
Each tool targets a distinct resource or action: session snapshot, track details, spectral capture, plugin library, mix analysis, device parameter setting, bypass toggling, group creation, routing changes, and health monitoring. No two tools have overlapping purposes; the descriptions clearly differentiate them.
All tool names follow a consistent verb_noun pattern: get_* for read-only operations, set_* for value changes, toggle_* for binary state, create_* for new objects, and analyze_* for analysis. The naming is uniform and predictable.
With 10 tools, the server is well-scoped for its purpose of Ableton session mixing assistance. Each tool serves a clear function, and the count is neither sparse nor overwhelming.
The tool set covers session reading, detailed track inspection, spectral analysis, plugin discovery, mix analysis, device parameter control, bypass toggling, group track creation, routing changes, and health monitoring. Minor gaps exist for track-level volume/pan/mute/solo controls, but the core mixing workflow is well-covered.
Maintenance
Related MCP Connectors
Remote MCP server for audio stem separation, denoise, reverb, and MIDI export.
MCP server for Producer/Riffusion AI music generation
Compose, mix, master and export in Logic Pro, REAPER or Ableton Live by talking to an AI engineer.
AI mixing and mastering in the chat: check a song, mix your stems, change the mix in plain words.
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP server for Ableton Live that exposes the Live Object Model to LLMs, enabling natural language control of music production.3684 npm11MIT
- AlicenseAqualityDmaintenanceMCP server that bridges Ableton Live with AI models, enabling real-time project inspection and control such as track overview, device parameters, and audio analysis.1236 PyPI1MIT
- AlicenseNot gradedqualityCmaintenanceMCP server that enables natural language control of Ableton Live for music production, including track, clip, device, automation, and mixing operations.9MIT
- AlicenseBqualityDmaintenanceAn MCP server that enables natural language control of Ableton Live, including session/transport, track management, MIDI clips and notes, devices, automation, browser integration, and audio generation via ElevenLabs.71MIT