Latest insights, tutorials, and updates from the Model Context Protocol team
NextChat is a light and fast AI assistant client, built in TypeScript, that supports MCP. It offers a privacy-first, local-data experience for interacting with self-deployed LLMs like RWKV-Runner or LocalAI across Web, iOS, MacOS, Android, Linux, and Windows platforms.
JavaGuide is an AI-powered MCP Client written in Java, designed to assist backend developers with interview preparation. It integrates a large language model (LLM) for an AI intelligent interview platform and RAG knowledge base, covering computer basics, databases, distributed systems, high concurrency, and system design. Developers seeking a structured approach to Java backend interviews will find it useful.
graphify transforms any codebase, including docs and schemas, into a queryable knowledge graph. It exposes this graph as an MCP Server, enabling deterministic AST parsing and rich cross-file insights for tools like Claude Code and Cursor.
The ai MCP Client is a TypeScript toolkit for building AI-powered applications across Next.js, React, Svelte, and Vue. It provides a unified API for interacting with various model providers and UI hooks for chatbots, streamlining MCP integration for web developers.
The prompt-eng-interactive-tutorial MCP Server offers a Jupyter Notebook-based course to master Claude prompt engineering. Developers can learn to build strong prompts, recognize failure modes, and understand Claude's strengths and weaknesses through interactive exercises and an Example Playground.
playwright-mcp is an MCP Server that enables LLMs to interact with web pages using Playwright's accessibility tree, offering fast and deterministic browser automation. It solves the problem of integrating LLMs with web UIs without relying on vision models or screenshots. Developers building LLM agents for web tasks should consider it.