Vibe Composer MIDI MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| list-midi-outputsC | Lists MIDI outputs |
| playC | Plays a music score |
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 2 tools
The two tools have clearly distinct purposes: one lists MIDI outputs (a discovery/query function), and the other plays a music score (an action/execution function). There is no overlap or ambiguity between them.
The naming is inconsistent: 'list-midi-outputs' uses kebab-case with a verb-noun structure, while 'play' is a single verb without a noun. This mix of conventions lacks a predictable pattern.
With only 2 tools, the server feels too thin for a 'Vibe Composer MIDI' domain, which suggests music composition or playback. Key operations like creating, editing, or stopping scores are missing, making the set underpowered.
The tool surface is severely incomplete for MIDI composition/playback. There are no tools to create, edit, save, load, or stop scores, and no control over playback (e.g., pause, volume). This will cause agent failures in typical workflows.