IRCAM Amplify MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| IRCAM_AMPLIFY_API_KEY | Yes | Your IRCAM Amplify API key from app.ircamamplify.io |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_musicA | Analyze an audio file to extract genre, mood, tempo, key, and detected instruments. Accepts a public URL to an audio file (MP3, WAV, FLAC, OGG, M4A). Returns structured tags useful for music classification and discovery. |
| separate_stemsA | Separate an audio file into individual stems: vocals, drums, bass, and other instruments. Accepts a public URL to an audio file (MP3, WAV, FLAC, OGG, M4A). For longer files, returns a job_id for async processing - use check_job_status to monitor progress. |
| detect_ai_musicA | Detect whether an audio file was generated by AI or created by humans. Accepts a public URL to an audio file (MP3, WAV, FLAC, OGG, M4A). Returns a confidence score (0-100) and classification (ai_generated, human_made, or uncertain). |
| analyze_loudnessA | Analyze the loudness of an audio file following EBU R128 standard. Accepts a public URL to an audio file (MP3, WAV, FLAC, OGG, M4A). Returns integrated loudness (LUFS), true peak (dB), and loudness range (LU). |
| check_job_statusA | Check the status of an async processing job. Use this to monitor jobs returned by separate_stems and other async operations. Returns job status (pending, processing, completed, failed), progress percentage, and results when completed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a clearly distinct purpose with no overlap: analyze_loudness focuses on loudness metrics, analyze_music on musical features, detect_ai_music on AI detection, separate_stems on audio separation, and check_job_status on job monitoring. The descriptions clearly differentiate their functions, eliminating any ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., analyze_loudness, check_job_status). This uniformity makes the tool set predictable and easy to understand, with no deviations in naming conventions.
With 5 tools, the server is well-scoped for audio analysis and processing. Each tool serves a specific, non-redundant function, and the count is appropriate for covering core operations without being overwhelming or insufficient.
The tool set covers key audio analysis tasks (loudness, music features, AI detection, stem separation) and includes job status checking for async operations. A minor gap is the lack of tools for audio editing or synthesis, but the provided tools support a complete workflow for analysis and processing within the stated domain.