Gizmos Audacity

io.github.gizmos-questPublished by GitHub account gizmos-questv0.1.0Updated Oct 24, 2026

Safe local audio editing, analysis and production in Audacity 3.7 through mod-script-pipe.

VerifiedSTDIODesktop onlyDeveloper ToolsMedia & Design

Overview

AI-generated overview

Local MCP server that lets an assistant edit, process, label, export and measure audio in a running Audacity 3.7 through mod-script-pipe.

What you can do
  • Launch, inspect and control the Audacity session: status, project info, windows, dialogs, recovery, quit.
  • Import audio, select, edit tracks and clips, apply fades and envelopes, export mixes and projects.
  • Generate audio, apply effects, capture noise profiles, run cleanup pipelines, auto-duck, macros and batch jobs.
  • Create and read labels, export label regions, and write label files.
  • Measure peak/RMS and optional LUFS or true peak, compare files, check silence and contrast, probe file metadata, and inspect history and preferences.
When to use it
Useful when you want an assistant to work on real audio projects in Audacity on your own machine: importing recordings, running cleanup or effect chains, adding chapter labels, exporting mixes, and checking loudness before delivery.
Requirements
Runs locally over stdio via npx, on desktop only. Needs Node.js 24.21 or newer running as the same user as Audacity, and English Audacity 3.7.x (3.7.8 reference, 3.7.9 verified) with mod-script-pipe enabled; Audacity 4 is not supported. Optional ffmpeg/ffprobe for LUFS, true peak, other formats and metadata. Optional AUDACITY_EXE, AUDACITY_CONFIG, AUDACITY_FFMPEG and AUDACITY_FFPROBE paths.
Before you install
Scripted effects create no individual undo entries and existing project save paths are refused, so save a new .aup3 backup before destructive processing. A timeout can leave an edit completed or still running. mod-script-pipe trusts any local process running as your user, so keep one controller. Effects can take ten minutes; set a longer client tool timeout. The server never downloads runtimes or kills Audacity.

Installation

In SourceWeft

  1. Open Gizmos Audacity in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Gizmos Audacity MCP

Local MCP tools for editing, processing and measuring audio in Audacity.

[Node 24.21+] [MIT]

45 typed tools · Audacity 3.7.x · Node 24.21+ · stdio

Import audio, edit tracks and clips, apply effects, write labels, export mixes, and measure peak/RMS or optional LUFS/true peak. Audacity does the processing. Windows supports hidden windows and native dialog recovery. macOS/Linux support the scripting FIFOs; their native window lifecycle is not qualified.

Requirements

  • English Audacity 3.7.x with mod-script-pipe enabled: 3.7.8 is the reference build (bundled catalogue, parameter limits, source audit) and 3.7.9 is verified; other patch levels are refused until verified. On Windows, install and pin it: winget install --id Audacity.Audacity -e --version 3.7.8, then winget pin add --id Audacity.Audacity -e --version 3.7.8.
  • Audacity 4 is not supported: 4.0 removed the scripting interface (mod-script-pipe). Support would be reconsidered only if Audacity ships a scripting host with full control.
  • Node.js 24.21 or newer, running as the same user as Audacity.
  • Optional ffmpeg/ffprobe for LUFS, LRA, true peak, other file formats and metadata. Native PCM/float WAV measurement needs neither.

Quick start

The npm package is @gizmos-quest/audacity-mcp. For a source checkout, run npm ci, then npm run build; use node dist/main.js as the server command.

  1. Install Audacity 3.7.8. Enable mod-script-pipe in Preferences → Modules, choose English in Preferences → Interface, and turn off Preferences → Application → Check for updates (update notices are modal and block scripting until closed). Restart Audacity.

  2. Check setup:

    sh
    npx -y @gizmos-quest/audacity-mcp doctor

    With Audacity stopped, doctor --fix can enable the scripting module. It saves a config backup first. Setup and configuration.

  3. Add the local server to your client using a snippet below, then restart the client if it requires that. Keep one server in control of the shared pipe.

Clients

Claude Code

sh
claude mcp add --scope user --transport stdio audacity -- npx -y @gizmos-quest/audacity-mcp

Claude Desktop / Cursor — add this to the client's MCP configuration:

json
{  "mcpServers": {    "audacity": {      "command": "npx",      "args": ["-y", "@gizmos-quest/audacity-mcp"]    }  }}

VS Code — .vscode/mcp.json:

json
{  "servers": {    "audacity": {      "type": "stdio",      "command": "npx",      "args": ["-y", "@gizmos-quest/audacity-mcp"]    }  }}

Codex — ~/.codex/config.toml:

toml
[mcp_servers.audacity]command = "npx"args = ["-y", "@gizmos-quest/audacity-mcp"]startup_timeout_sec = 90tool_timeout_sec = 900

Effects can take ten minutes; allow a longer client tool timeout. See client setup for official references and Windows command resolution. Troubleshooting covers missing pipes and localized plugin IDs.

First prompt

Check Audacity's status and launch it if stopped. Import my voice recording as Voice. Measure it, then show a dry-run voice cleanup plan without normalization or noise reduction. Ask before applying it and save a project backup first.

A pipeline preview takes a named or zero-based track reference:

json
{"track":"Voice","preset":"voice","dryRun":true,"loudness":"none"}

Try the reproducible voice-over example: generated audio, reviewed cleanup, a ducked bed, chapters/subtitles and measured delivery. Its opt-in runner drives the built server over stdio against live Audacity.

Tools

GroupTools
Session and discoverylaunch, fresh, quit, window, dialogs, recover, status, project_info, info, describe
Edit and mixselect, import, export, project, track_set, track_edit, clip_move, clip_set, edit, fade, envelope_set
Processgenerate, effect, noise_profile, pipeline, auto_duck, command, menu, macros, batch
Labelslabels_set, labels, labels_file, label_regions_export
Measure and controlmeasure, measure_file, compare_files, loudness_target, silence, contrast, probe_file, targets, transport, history, preferences

Every name starts with audacity_. Tool reference includes arguments and units; the capability matrix lists limits.

Safety

  • Save a new .aup3 backup before destructive processing. Scripted effects do not create individual undo entries. Existing project save paths are refused.
  • Strict inputs and a reviewed catalogue block known modal commands. Hidden Audacity still runs its UI and audio engine; it has no native headless mode.
  • A timeout can leave an edit completed or still running. Inspect dialogs, use explicit recovery, then inspect the project before deciding what to do.
  • Noise reduction requires fresh process state and an explicit room-tone capture; normalization, limiting and timing changes stay explicit.
  • mod-script-pipe trusts local processes running as your user. Use one controller. The server never downloads runtimes/models or kills Audacity.

Native safety limits · Effect requirements · Testing · Architecture · Contributing · Security

MIT licensed. Research and source attribution are in NOTICE.md. Audacity is a trademark of Muse Group; this project is unaffiliated.

Source: README.md at commit 2699244

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestOct 11, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts