mcp-audio-server
0
MCP Audio Server is designed to process audio files, offering features such as tempo detection, key detection, and chord analysis. It provides a RESTful API for easy integration and supports structured logging and metrics for observability.
MCP Audio Server
A Model Context Protocol (MCP) server for audio processing and chord analysis.
Features
- Audio file decoding and normalization with FFmpeg
- Music analysis capabilities:
- Tempo detection (BPM)
- Key detection
- Chord analysis and tracking
- RESTful API with structured responses
- JSON schema validation for inputs and outputs
- Robust error handling with descriptive messages
- Resource management with concurrency controls
- Caching for performance optimization
- Observability with structured logging and metrics
- Comprehensive test suite
- Containerized deployment with Docker
Installation
Docker (Recommended)
Use Docker Compose for the quickest setup:
Manual Installation
-
Prerequisites:
- Python 3.10 or higher
- FFmpeg
- Poetry
-
Install dependencies:
-
Run the server:
API Documentation
The full OpenAPI specification is available at /docs when the server is running:
Endpoints
POST /analyze_chords: Analyze audio for chords, key, and tempoGET /health: Health check endpointGET /ready: Readiness check for load balancersGET /metrics: Prometheus metrics (redirects to metrics server)
License and Compliance
This project is licensed under the MIT License.