Chatty MCP
Click on "Deploy 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., "@Chatty MCPSummarize the last AI response"
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.
Chatty MCP
Oh, hello there! Meet Chatty MCP, your new best buddy who loves to chat out loud! After every request in Cursor, Cline, or any MCP-supported editor, it will speak up and summarize what was just done. Not only will you know when your long request has completed, but you can also use another sense to quickly understand what the editor produced, integrating deeply with your workflow for a better coding experience.
Check out our main website for documentation, demos, and configuration: https://chatty-mcp.vercel.app/

Why?
Waiting for Cursor to complete your requests can be tedious - you're just staring at a black screen. With Chatty MCP, you can Alt+Tab to another window while Cursor is thinking, and return when you hear the voice announcement.
You don't need to read everything produced by your AI - just listen to the summary and quickly decide if it's going in the right direction, then make adjustments as needed.
Having your computer interact with you by voice is an interesting coding experience.
Additionally, this gives you the ability to customize the voice. Use your system's built-in TTS for convenience, Kokoro TTS for smooth and natural voice output, or even Fish TTS for anime-style voices in the future.
Related MCP server: mcp-tts
How to Get and Configure Chatty
I don't like extremely long READMEs as documentation, so visit our site for everything you need to know: https://chatty-mcp.vercel.app/docs/welcome
Note
For Kokoro ONNX model to work, you must download the Kokoro model and place it in the correct directory. Check the documentation's Speech Engine section for more information.
Made with 💖 by folks who believe every computer needs a voice!
This server cannot be deployed
Maintenance
Related MCP Connectors
Carbon Voice MCP serves as a bridge that connects AI assistants like ChatGPT, Claude, and Cursor to a user's Carbon Voice account, turning voice messages and conversations into a private, on-demand knowledge base. It provides 28 specialized tools for comprehensive voice messaging management, including creating and sending messages, accessing conversation history with instant transcription, running AI actions (summarization, TLDR generation, meeting notes), and managing workspace collaboration through folders, contacts, and team communications.
AI voice generation: text-to-speech and voice cloning from any MCP client.
Voice-powered bug reporting with 13 MCP tools. Record bugs by talking; let AI find and fix them.
Speech, transcription, voice agents, Trace, Recap, dubbing and narration with browser OAuth.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables coding agents to speak aloud using text-to-speech functionality. Works with agents running inside devcontainers and provides configurable voice settings for creating chatty AI companions.5-
- AlicenseNot gradedqualityDmaintenanceAdds text-to-speech capabilities to Cursor IDE, allowing your AI assistant to speak responses, summaries, and explanations out loud using OpenAI or ElevenLabs.1Apache 2.0
- AlicenseNot gradedqualityDmaintenanceProvides sound alerts, voice messages, and macOS notifications for Claude Code and other MCP-compatible AI assistants.12 npmMIT
- AlicenseNot gradedqualityDmaintenanceMulti-engine text-to-speech for AI coding assistants. Speaks responses aloud from Claude Code, Cursor, or VS Code via a Claude Code plugin, MCP server, or CLI pipe.MIT