About Audacity MCP Server
Audacity MCP Server is an MCP server that controls the Audacity audio editor through mod-script-pipe. It exposes many Audacity scripting commands as MCP tools and uses stdio transport. It suits users who want MCP clients to automate audio editing tasks.
Key features
- 01Connects to Audacity via mod-script-pipe
- 02Exposes many Audacity scripting commands as tools
- 03Uses stdio transport
- 04Auto-detects pipe suffixes in /tmp
Use cases
- 01Letting an MCP client drive Audacity for audio editing
- 02Running Audacity commands from natural language requests
MCP support
This project is an MCP server that provides Audacity scripting commands as MCP tools for MCP clients to call.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAudacity MCP Server
MCP (Model Context Protocol) server for controlling Audacity through mod-script-pipe.
This server communicates with Audacity over named pipes and exposes many Audacity scripting commands as MCP tools.
Features
- Connects to Audacity via
mod-script-pipe - Exposes a broad set of Audacity commands as MCP tools
- Uses
stdiotransport (works with Codex/Claude/Desktop clients) - Auto-detects pipe suffixes in
/tmp(for example.501)
Requirements
- Audacity 3.x+
- Python 3.10+
mod-script-pipeenabled in Audacity
Install
git clone https://github.com/An-3/mcp-audacity.git
cd mcp-audacity
./scripts/setup.sh
Quick local test (no MCP host needed)
# 1) Start Audacity and enable mod-script-pipe (see section below)
# 2) Verify local connectivity:
./scripts/smoke_test.sh
# 3) Start MCP server:
./scripts/run.sh
If you prefer manual setup instead of scripts:
python3 -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip
python -m pip install "mcp[cli]>=1.6.0" "httpx>=0.28.1"
Optional (install as package + CLI entrypoint):
pip install .
audacity_mcp_server
Enable mod-script-pipe in Audacity
- Open Audacity.
- Open the Modules preferences page:
- Windows/Linux:
Edit -> Preferences -> Modules - macOS:
Audacity -> Settings... -> Modules(orAudacity -> Preferences -> Modulesdepending on build)
- Windows/Linux:
- Set
mod-script-pipefromNew(orDisabled) toEnabled. - Restart Audacity.
Note: In current Audacity versions, this is configured in Modules, not in a separate "Scripting/Remote Control" section.
Verify pipes exist:
ls -l /tmp/audacity_script_pipe.to.* /tmp/audacity_script_pipe.from.*
If the files are present, Audacity is ready.
Run the server manually
./scripts/run.sh
Expected startup logs include:
Audacity MCP server starting upOpened Audacity mod-script-pipeConnected to Audacity mod-script-pipe
Connect from Codex
Add server to Codex MCP config:
codex mcp add AudacityMCP -- /absolute/path/to/mcp-audacity/.venv/bin/python /absolute/path/to/mcp-audacity/audacity_mcp_server.py
List configured MCP servers:
codex mcp list
Connect from Claude Desktop
Example claude_desktop_config.json:
{
"mcpServers": {
"audacity": {
"command": "/absolute/path/to/mcp-audacity/.venv/bin/python",
"args": [
"/absolute/path/to/mcp-audacity/audacity_mcp_server.py"
]
}
}
}
Troubleshooting
Failed to open Audacity pipes:- Confirm Audacity is running.
- Confirm
mod-script-pipeisEnabled. - Confirm pipe files exist in
/tmp.
spawn uv ENOENT:- Use absolute paths in client config, or use the Python command shown above instead of
uv.
- Use absolute paths in client config, or use the Python command shown above instead of
- Server starts but tools behave inconsistently:
- Ensure you are using this latest version, which sends commands in
Command:form and reads full responses untilBatchCommand finished.
- Ensure you are using this latest version, which sends commands in
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.