Happy slice of mcp pizzaMCP.pizza

CarrotAI

MCP.Pizza Chef: Xingsandesu

CarrotAI is an advanced AI agent client that enables real-time streaming chat using Server-Sent Events (SSE) with integrated Model Control Protocol (MCP) support. It allows concurrent connections to multiple SSE MCP servers, providing seamless multi-server interaction. The client features multilingual user interfaces in English, Chinese, and Japanese, built with a Flutter frontend and FastAPI backend for responsive and scalable AI-driven conversations.

Unmaintained Β· No commits in 16 months.

Use This MCP client To

Connect to multiple SSE MCP servers concurrently for real-time chat Stream AI-generated responses instantly via Server-Sent Events Use multilingual interfaces in English, Chinese, and Japanese Integrate with various MCP servers for flexible AI workflows Deploy as a SaaS client for scalable AI agent access Enable seamless multi-server AI agent conversations

README

CarrotAI

CarrotAI Logo

AI Agent with Multi-Server Streaming & Multi-Language Support

Flutter Frontend + FastAPI Backend

πŸš€ Experience online now | SaaS Client download

πŸ‡¨πŸ‡³ ι˜…θ―»δΈ­ζ–‡ζ–‡ζ‘£

πŸ₯• Introduction

CarrotAI is a cutting-edge AI agent application that delivers real-time streaming chat via Server-Sent Events (SSE) and streamable HTTP with built-in Model Control Protocol (MCP) integration. It supports concurrent connections to multiple SSE MCP servers and provides user interfaces in English, Chinese, and Japanese.

πŸš€ Features

  • AI Agent: Real-time chat powered by SSE and MCP adapters for a seamless conversational experience.
  • Multi-Server Support: Connect to and call multiple SSE MCP servers simultaneously to aggregate intelligent responses.
  • Multi-Language: Full localization in English, δΈ­ζ–‡ (Chinese), and ζ—₯本θͺž (Japanese).
  • Deep Thinking Mode: Advanced analysis for complex or multi-step queries.
  • Authentication: Secure login/register flow using JWT tokens.
  • Responsive UI: Adaptive design for mobile, desktop, and web platforms.
  • Theme Customization: Light/dark mode, custom seed colors, and dynamic Material 3 theming via dynamic_color.
  • File Upload: Attach and parse files within conversations for richer context.

πŸ€– Supported Model APIs

  • DeepSeek: Advanced language model with strong reasoning capabilities

πŸ› οΈ Tech Stack

CarrotAI FAQ

How does CarrotAI handle real-time streaming chat?
CarrotAI uses Server-Sent Events (SSE) to deliver real-time streaming chat, ensuring low-latency, continuous message updates from MCP servers.
Can CarrotAI connect to multiple MCP servers simultaneously?
Yes, CarrotAI supports concurrent connections to multiple SSE MCP servers, enabling multi-server AI interactions.
What languages does CarrotAI support for its user interface?
CarrotAI provides user interfaces in English, Chinese, and Japanese, catering to a diverse user base.
What technologies power CarrotAI's frontend and backend?
CarrotAI uses Flutter for its frontend and FastAPI for its backend, combining cross-platform UI with a performant Python server.
Is CarrotAI suitable for SaaS deployment?
Yes, CarrotAI offers a SaaS client version, making it easy to deploy scalable AI agent services.
How does CarrotAI integrate with the Model Control Protocol?
CarrotAI has built-in MCP integration, allowing it to manage context flow and tool calling across connected MCP servers.
Can CarrotAI be used with different LLM providers?
Yes, CarrotAI's MCP integration supports models from providers like OpenAI, Anthropic Claude, and Google Gemini.
Does CarrotAI support streamable HTTP besides SSE?
Yes, CarrotAI supports both Server-Sent Events and streamable HTTP for flexible real-time data streaming.