Click on "Install 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., "@Audio Analysis MCP Servercompare original.wav and edited.wav to find the RMS and spectral differences"
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.
Audio Analysis MCP Server
An MCP server that gives Claude Code the ability to analyze audio files without ears. Provides numerical fingerprints, visual spectrograms, pitch tracking, and more - all through a single, token-efficient tool.
Overview
This server exposes one tool (audio_analyze) with multiple operations, keeping the MCP schema small and token usage minimal. Visual outputs (spectrograms, waveforms, etc.) are saved to disk and paths returned - Claude can then read the images separately if needed.
Installation
If you don't have uv:
Configuration
Add to your project's .mcp.json:
Or add to ~/.claude.json to make it available globally.
Operations
Single tool: audio_analyze(path, op, [path2])
Numerical Analysis
Op | Description | Output |
| RMS, peak, spectral stats |
|
| Estimated F1-F4 frequencies |
|
| Compare two files numerically |
|
| Sample-level difference |
|
| Detect transients/attacks |
|
| Fingerprint multiple files |
|
Visual Analysis
Op | Description | Output |
| Mel spectrogram image |
|
| Amplitude over time |
|
| 3D spectral surface |
|
| F0 tracking plot + stats |
|
Output Directory
Images are saved to the directory specified by AUDIO_ANALYSIS_OUTPUT_DIR env var. Defaults to ~/.audio-analysis-mcp if not set.
Claude Code Skill & Slash Command
This project includes a Claude Code skill and slash command for structured audio comparison workflows.
Installing the Skill
Copy the skill to your Claude Code skills directory:
This enables automatic detection when you're comparing audio files, with structured workflows for:
Running all 7 analysis types in parallel
Building metrics comparison tables
Tracking improvements across versions
Pattern detection (oscillation, trade-offs, plateaus)
Installing the Slash Command
Copy the slash command to your Claude Code commands directory:
Then use it with:
Quick Install (Both)
Dependencies
mcp- Official MCP Python SDKlibrosa- Audio analysismatplotlib- Visualizationsnumpy,scipy- Numerical operations