Cursor Sound MCP
Used for package management and running scripts to install dependencies, build, and start the MCP server
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Cursor Sound MCPplay the success sound effect"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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
Related MCP server: MCP Sound Tool
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
Install dependencies:
npm installAdd your sound effects: Place your sound files in the
soundsdirectory. The default expected sound is:
sounds/completion.mp3- Played after code generation
You can find free sound effects on freesound.org.
Build the project:
npm run buildUsage
Run the MCP server:
npm startThe server will start and listen for events from Cursor through the stdio transport.
Configuration
The sound effects and volume can be customized by:
Replacing the sound files in the
soundsdirectoryModifying the sound file paths in
src/index.ts
Development
For development with auto-recompilation:
npm run devAvailable Tools
1 toolplayCompletionSoundC
Plays a completion sound when called
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It states the tool plays a sound, implying an auditory output, but doesn't disclose behavioral traits like whether it requires audio permissions, if it blocks execution, error handling, or what happens on failure. This is a significant gap for a tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with no wasted words. It's appropriately sized for a simple tool and front-loaded with the core action. Every word earns its place, making it highly concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (0 parameters, no output schema), the description is incomplete. It lacks context about the sound's source, volume, duration, or system requirements. With no annotations to fill gaps, the description should provide more detail to ensure the agent understands how to invoke it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has 0 parameters, and schema description coverage is 100% (as there are no parameters to describe). The description doesn't need to add parameter semantics, so a baseline score of 4 is appropriate, reflecting that no additional information is required beyond the empty schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool's purpose ('Plays a completion sound when called'), which is clear but vague. It specifies the action ('Plays') and resource ('a completion sound'), but lacks detail about what constitutes a 'completion sound' or how it's played. With no sibling tools, differentiation isn't needed, but the purpose remains somewhat ambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool. It doesn't specify appropriate contexts (e.g., after a task finishes), prerequisites, or alternatives. With no sibling tools, this isn't a comparative issue, but the lack of any usage context leaves the agent without direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
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.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Generate AI images, videos, music, SFX & speech in any AI assistant. Results appear inline in chat.
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.
Related MCP Servers
- FlicenseDqualityDmaintenanceProvides audio feedback by playing sound effects when Cursor AI completes code generation, creating a more interactive coding experience.119
- AlicenseAqualityFmaintenanceA Model Context Protocol implementation that plays sound effects (completion, error, notification) for Cursor AI and other MCP-compatible environments, providing audio feedback for a more interactive coding experience.31MIT
- AlicenseNot gradedqualityFmaintenanceProvides audio playback functionality for AI agents, allowing them to play notification sounds when coding tasks are completed.1MIT
- AlicenseBqualityDmaintenancePlays sound effects (completion, newtype, and error sounds) in response to various situations like task completion, insights, or errors. Integrates with Claude Desktop to provide audio feedback for improved workflow efficiency and entertainment.2196MIT
Appeared in Searches
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bcharleson/sound-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server