Skip to main content
MCP server CX Codex

ferraus — Claude Code MCP server: what it does, how to install

The ferraus MCP server for Claude Code runs audio editing and mastering commands with JSON output.

Apache-2.0 ★ 6 updated 2026-11-16

Install into Claude Code · Platform CLI All methods and platforms ↓
claude mcp add ferraus -- docker run -i --rm ghcr.io/djynnius/ferraus:v0.1.5
Open on GitHub

What ferraus does

The utility handles stem separation, restoration, tuning, and mastering through a single binary. Every command returns versioned data and sidecar files so tasks run without a graphical interface.

Running the server requires Docker and the container image ghcr.io/djynnius/ferraus:v0.1.5. Agents interact using the --json contract, dry runs, and explicit model download permissions.

Companion skills add workflows for unsupervised mixing, vocal polishing, and beat generation.

What it helps with

  • separate audio into individual stems
  • denoise audio recordings
  • master tracks for streaming targets
  • pitch-correct vocal tracks

Example prompts for the agent

  • Split the audio file into stems using ferraus
  • Denoise the vocal take and save the result
  • Master the final mix for streaming

How to install ferraus

Platform CLI

claude mcp add ferraus -- docker run -i --rm ghcr.io/djynnius/ferraus:v0.1.5

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about ferraus

How to install ferraus in Claude Code?

Run claude mcp add ferraus -- docker run -i --rm ghcr.io/djynnius/ferraus:v0.1.5 in your terminal.

What does ferraus do?

It processes, repairs, mixes, and masters audio files via command-line arguments and returns structured JSON output.

What is required to run ferraus?

Running the MCP server requires Docker installed on your system.

Similar MCP servers

All MCP servers for AI and ML →

Project sponsors

Companies that keep this analytics open