Latest insights, tutorials, and updates from the Model Context Protocol team
awesome-llm-apps is a Python-based MCP Client that aggregates LLM applications featuring AI Agents and RAG. It solves the problem of integrating diverse data sources and services via MCP, enabling developers to build sophisticated AI workflows across platforms like GitHub and Notion.
FunASR is a Python-based MCP Server offering industrial-grade speech recognition, speaker diarization, and emotion detection. It provides a 170x real-time processing speed and supports over 50 languages, making it suitable for developers needing high-performance, multilingual audio processing.
chatbox is a user-friendly desktop MCP Client for AI models, centralizing access to GPT, Claude, Gemini, and Ollama. It solves the problem of managing multiple LLM providers and local models with data privacy, offering image generation and advanced prompting features for developers.
agentscope is a Python-based MCP Client for building LLM-powered multi-agent applications, offering a drag-and-drop workstation and actor-based distribution. It simplifies complex agent system development with robust fault-tolerance and broad model compatibility.
xiaohongshu-mcp is a Go-based MCP Server designed to enable AI assistants to directly access data from xiaohongshu.com. It offers flexible deployment options, including deep integration with Openclaw for developers and a zero-configuration browser plugin for non-technical users, simplifying access to Xiaohongshu data via MCP.
litellm is a Python SDK and MCP Server acting as an LLM Gateway, allowing developers to call over 100 different LLM APIs using a consistent OpenAI format. It solves the fragmentation challenge of integrating various AI models, making it ideal for developers building applications that need flexible access to multiple large language models.