Cursor Sound MCP
# Cursor Sound MCP
A Model Context Protocol (MCP) implementation that plays sound effects after Cursor AI completes code generation. This MCP integrates with Cursor to provide audio feedback for a more interactive coding experience.
Inspired by @EricListin on X.com - I have made some changes to the code to not error out and be online.
## Features
- Plays a sound effect when Cursor completes code generation
- Uses the Model Context Protocol (MCP) for standardized integration
- Configurable sound effects
- Improved error handling and logging
- Stable JSON response format
## Cursor Rules
Add this to your Cursor custom instructions:
"EVERY TIME you finish any task or you need something from me, run the sound-mcp MCP server to get my attention."
## Installation
1. Install dependencies:
```bash
npm install
```
2. Add your sound effects:
Place your sound files in the `sounds` directory. The default expected sound is:
- `sounds/completion.mp3` - Played after code generation
You can find free sound effects on freesound.org.
3. Build the project:
```bash
npm run build
```
## Usage
Run the MCP server:
```bash
npm start
```
The server will start and listen for events from Cursor through the stdio transport.
## Configuration
The sound effects and volume can be customized by:
1. Replacing the sound files in the `sounds` directory
2. Modifying the sound file paths in `src/index.ts`
## Development
For development with auto-recompilation:
```bash
npm run dev
```
TDQS
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The single tool has a clear, distinct purpose that cannot be mistaken for another.
A single tool inherently has perfect naming consistency, as there are no other names to compare it against. The tool name 'playCompletionSound' follows a clear verb_noun pattern.
One tool is too few for a server's purpose, as it severely limits functionality and suggests the server is trivial or incomplete. A single sound-playing tool does not justify a full MCP server.
The server is severely incomplete, as it only offers a single sound-playing tool with no other related operations (e.g., stop sound, list sounds, adjust volume). This minimal surface fails to cover any meaningful domain.