tone-listener-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Enable Gemini uploads and listening; omit for local-only operation | |
| TONE_LISTENER_MODEL | No | Audio-capable Gemini model available to your account | gemini-3.8-flash |
| TONE_LISTENER_MAX_SECONDS | No | Maximum selected duration; positive finite seconds | 600 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Tools for listening to and comparing guitar tone recordings.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| server_infoA | Return basic information about this server. |
| audio_metricsB | Measure local audio levels, spectrum and stereo. Times are seconds; end is exclusive. |
| analyze_audioC | Measure a clip and optionally upload it to Gemini for guitar listening. |
| compare_audioC | Compare B to reference A with RMS matching and optional Gemini A/B listening. |
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 4 tools
audio_metrics and analyze_audio both measure audio levels/spectrum and differ mainly by an optional Gemini upload step, which makes misselection likely. compare_audio and server_info are clearly distinct, so overlap is limited to one ambiguous pair.
Names are readable but follow mixed conventions: two noun-style names (server_info, audio_metrics) and two verb_noun names (analyze_audio, compare_audio). No camelCase chaos, but there is no single predictable pattern for an agent to rely on.
Four tools is a tight, focused surface for an audio-analysis server, and each tool maps to a plausible workflow. server_info is arguably filler, keeping it from a 5.
The surface covers measurement, single-clip analysis, and A/B comparison, but there is no tool for recording, streaming/live monitoring, or device/input selection despite the 'listener' framing. Agents would hit a dead end on any real-time or capture workflow.