Happy slice of mcp pizzaMCP.pizza

multimodal-mcp-client

MCP.Pizza Chef: Ejb503

Retired and now frozen read-only on GitHub, this project has been folded into systemprompt-template and systemprompt-core, which its authors point everyone toward instead. While it was alive you spoke to it in a browser tab and it ran tools from whichever MCP servers you listed in its settings file, answering out loud. It wanted two separate keys, one from Google and one from systemprompt.io, and it never worked in Safari. There is little reason to start with it today.

Archived · archived read-only, work moved to systemprompt-template
Communication
Other

Use This MCP client To

Talk to my assistant out loud instead of typing Hear answers read back while my hands are busy Run tools from my own MCP servers by voice Try voice control before committing to a bigger build Show someone what a hands-free assistant feels like

README

⚠️ Deprecated — no longer maintained

This repository has been superseded. All new development and support lives in:

Learn more at systemprompt.io.

The original README is preserved below for historical reference.

Systemprompt Multimodal MCP Client

A modern voice-controlled AI interface powered by Google Gemini and Anthropic MCP (Model Control Protocol). Transform how you interact with AI through natural speech and multimodal inputs.

⚠️ Important Note: This open source project is currently in development and in early access. It is not currently compatible with Safari but has been tested on Chrome with Linux, Windows, and MacOS. If you have any problems, please let us know on Discord or GitHub.

If you find this project useful, please consider:

  • ⭐ Starring it on GitHub
  • 🔄 Sharing it with others
  • 💬 Joining our Discord community

🌟 Overview

A modern Vite + TypeScript application that enables voice-controlled AI workflows through MCP (Model Control Protocol). This project revolutionizes how you interact with AI systems by combining Google Gemini's multimodal capabilities with MCP's extensible tooling system.

The Client supports both custom (user provided and configured) and Systemprompt MCP servers. Systemprompt MCP servers can be installed through the UX with a Systemprompt API key (free).

Custom MCP servers are not pre-configured and require a custom configuration file.

Create a local file mcp.config.custom.json in the config directory and add your MCP server configuration.

multimodal-mcp-client FAQ

Is this still maintained?
No. The project is archived and read-only, and its authors say all further work moved to systemprompt-template, which they name as the place to start, and systemprompt-core underneath it.
Should I install it anyway?
Only out of curiosity. Nothing will be fixed if it breaks, and the replacement projects are where any support now lives.
Does it need keys?
Yes, two of them. One from Google for the Gemini model, and one from systemprompt.io, whose own key is free to obtain.
Which browsers does it work in?
Chrome on Windows, Mac, or Linux. Safari was never supported, and the browser must handle speech input.
Can I use this to control my own tools by voice?
That was the whole idea. You listed your own MCP servers in a settings file and could then trigger them by speaking, with results read back to you.
How hard was it to set up?
Hard. You downloaded the project, installed its parts twice over, copied a settings file, added two keys, and started a local web server before anything appeared.