IRCAM Amplify MCP Server

# Quick Start: IRCAM Amplify MCP Server Get started with the IRCAM Amplify MCP Server in under 5 minutes. ## Prerequisites - **Node.js 18+** installed ([download](https://nodejs.org/)) - **IRCAM Amplify API Key** from [app.ircamamplify.io](https://app.ircamamplify.io) - An MCP-compatible client (Claude Desktop, Cline, etc.) ## Installation ### Option 1: npm (recommended) ```bash npm install -g ircam-amplify-mcp ``` ### Option 2: npx (no install) ```bash npx ircam-amplify-mcp ``` ### Option 3: From source ```bash git clone https://github.com/your-org/ircam-amplify-mcp.git cd ircam-amplify-mcp npm install npm run build ``` ## Configuration ### 1. Set your API key ```bash export IRCAM_AMPLIFY_API_KEY="your-api-key-here" ``` Or add to your shell profile (`~/.bashrc`, `~/.zshrc`): ```bash echo 'export IRCAM_AMPLIFY_API_KEY="your-api-key-here"' >> ~/.zshrc source ~/.zshrc ``` ### 2. Configure your MCP client #### Claude Desktop Add to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows): ```json { "mcpServers": { "ircam-amplify": { "command": "npx", "args": ["ircam-amplify-mcp"], "env": { "IRCAM_AMPLIFY_API_KEY": "your-api-key-here" } } } } ``` #### Cline (VS Code) Add to your Cline MCP settings: ```json { "ircam-amplify": { "command": "npx", "args": ["ircam-amplify-mcp"], "env": { "IRCAM_AMPLIFY_API_KEY": "your-api-key-here" } } } ``` ## Usage Examples Once configured, ask your LLM to use the IRCAM Amplify tools: ### Analyze a song > "Analyze this song and tell me its genre, mood, and tempo: https://example.com/song.mp3" The LLM will use `analyze_music` and return something like: ``` This track is Electronic/House at 128 BPM in A minor. The mood is energetic and uplifting, featuring synths, drums, and bass. ``` ### Separate stems for karaoke > "I want to create a karaoke version of this song. Please separate the vocals: https://example.com/track.mp3" The LLM will use `separate_stems` and return: ``` I've separated the stems. Here are the download links (valid 24h): - Vocals: [link] - Instrumental (drums + bass + other): [links] ``` ### Check if music is AI-generated > "Is this track AI-generated? https://example.com/mystery.mp3" The LLM will use `detect_ai_music` and return: ``` This track appears to be human-made with 87% confidence. ``` ### Analyze loudness for mastering > "Check if this master is ready for Spotify: https://example.com/master.wav" The LLM will use `analyze_loudness` and return: ``` Loudness analysis: - Integrated: -14.2 LUFS (Spotify target: -14 LUFS) ✓ - True Peak: -1.0 dB (below -1 dB limit) ✓ - Dynamic Range: 8.5 LU (good dynamics) This master is ready for Spotify! ``` ## Available Tools | Tool | Description | |------|-------------| | `analyze_music` | Extract genre, mood, tempo, key, instruments | | `separate_stems` | Split into vocals, drums, bass, other | | `detect_ai_music` | Detect AI vs human-made music | | `analyze_loudness` | Measure LUFS, peak, dynamic range | | `check_job_status` | Poll async operations | ## Troubleshooting ### "Missing API key" error Ensure `IRCAM_AMPLIFY_API_KEY` is set in your environment or MCP config. ### "Invalid API key" error Verify your key at [app.ircamamplify.io](https://app.ircamamplify.io). Keys may expire or be revoked. ### "Cannot access URL" error The audio URL must be: - Publicly accessible (no authentication required) - Direct link to audio file (not a streaming page) - Supported format: MP3, WAV, FLAC, OGG, or M4A ### Stem separation taking too long Stem separation is async for files > 30 seconds. The tool returns a `job_id`. Ask the LLM to "check the status" and it will poll until complete. ## Support - **Documentation**: [docs.ircamamplify.io](https://docs.ircamamplify.io) - **Issues**: [GitHub Issues](https://github.com/your-org/ircam-amplify-mcp/issues) - **IRCAM Support**: contact@ircamamplify.com