Which Audacity versions are supported?
AudacityMCP currently works with Audacity 3.x only. Audacity 4.x is not yet supported.
@xDarkzx
Basic information
AudacityMCP connects any MCP-compatible AI assistant to [Audacity](https://www.audacityteam.org/), giving it full control over audio editing through 131 tools and 9 pipelines spanning effects, cleanup, mastering, and more. Talk to your AI assistant and it edits your audio in real
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"audacity": {
"command": "audacity-mcp"
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
AudacityMCP connects any MCP-compatible AI assistant to Audacity, giving it full control over audio editing through 131 tools covering effects, cleanup, mastering, transcription, and more. Everything runs locally through Audacity's named pipe interface—no cloud, no API keys for audio processing. Works with Audacity 3.x only.
Download or clone the repository, then run the installer (install.bat on Windows, bash install.sh on macOS/Linux) to install audacity-mcp from PyPI, enable mod-script-pipe, and configure Claude Desktop automatically. For other MCP clients, install manually with pip install audacity-mcp and add to your client's MCP config. Audacity must be open first.
AudacityMCP currently works with Audacity 3.x only. Audacity 4.x is not yet supported.
No. All audio processing runs locally through Audacity's named pipe interface. No cloud, no API keys are needed for audio processing.
Pipelines only reduce peaks if they are too hot; they never boost loudness. After a pipeline, you can ask the AI to run `loudness_normalize` to hit a specific LUFS target (e.g., -14 for Spotify).
Local transcription is experimental and requires separate setup. Powered by faster-whisper, it runs entirely offline with 5 model sizes and supports multiple export formats (SRT, VTT, TXT). See the installation guide for detailed setup.
Yes. AudacityMCP communicates through Audacity's named pipe—it cannot launch Audacity for you.

A free remote MCP server for The Living Bread. Bible passages read word for word from a stored public domain text with an evidence label, keyword search and cross references, real churches, gatherings and prayer groups w

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.
Comments