Systemprompt Multimodal MCP Client

What is Systemprompt Multimodal MCP Client?

A modern voice-controlled AI interface powered by Google Gemini and the Anthropic Model Control Protocol (MCP). It runs in Chrome on Linux, Windows, and MacOS, and is designed for developers who want to build and use voice-first, multimodal AI workflows.

How to use Systemprompt Multimodal MCP Client?

Clone the repository, install dependencies (npm install in both root and proxy directories), create a local config file from the example, obtain a Google Gemini API key and a free Systemprompt API key, add them to .env with the VITE_ prefix, and start the development server with npm run dev. Custom MCP servers can be added by editing mcp.config.custom.json.

Key features of Systemprompt Multimodal MCP Client

• Natural voice control for AI workflows and commands
• Multimodal understanding of text, voice, and visual inputs
• Real-time voice synthesis for instant audio responses
• Extensible tool system through MCP server integration
• Workflow automation that chains multiple AI operations
• State management for complex, multi-step interactions

Use cases of Systemprompt Multimodal MCP Client

• Building voice-controlled AI applications with natural speech input
• Combining text, voice, and images in a single AI interaction
• Creating automated AI workflows that execute multiple steps via voice
• Integrating custom tools and data sources into AI conversations
• Prototyping and experimenting with multimodal AI on modern browsers

FAQ from Systemprompt Multimodal MCP Client

What browsers and platforms are supported?

The client has been tested on Chrome with Linux, Windows, and MacOS. It is not currently compatible with Safari.

What API keys are required to use the client?

You need a Google Gemini API key from Google AI Studio and a free Systemprompt API key from systemprompt.io/console. Both must be added to the .env file.

Can I use my own MCP servers with the client?

Yes. Custom MCP servers can be added by creating a mcp.config.custom.json file in the config directory and specifying the server command, arguments, and environment variables.

Is the client free and open source?

The project is open source under the MIT License. While the client code is free, the required API keys (Gemini and Systemprompt) may have their own usage fees or free tiers.

What is the current development status?

The project is in early access and active development. It may contain bugs or incomplete features; users are encouraged to report issues on Discord or GitHub.