Browse and discover Model Context Protocol compatible clients.
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.
An open-source AI agent that brings the power of Gemini directly into your terminal.
✨ Light and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows
🤯 Lobe Chat - an open-source, modern design AI chat framework. Supports multiple AI providers (OpenAI / Claude 4 / Gemini / DeepSeek / Ollama / Qwen), Knowledge Base (file upload / knowledge managemen
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
No description provided
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
Memory for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
Cherry Studio appears to be a software development tool or IDE, potentially focused on AI or creative applications, with multi-language support and links to documentation and community resources.
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Chrome DevTools for coding agents
An MCP client is an application that connects to MCP servers using the Model Context Protocol— the open standard that lets AI assistants use external tools and data. Clients include desktop chat apps like Claude Desktop, AI-powered code editors like Cursor and VS Code, agent frameworks, and custom applications. The client handles discovering a server's tools, passing them to the language model, and executing tool calls on the user's behalf.
This directory lists 520+ open-source MCP clients from GitHub with AI-analyzed descriptions, setup guides, and feature breakdowns. Consider where you work (terminal, IDE, desktop app, or web), which models the client supports, and whether it handles the MCP features you need — tools, resources, prompts, and sampling. GitHub stars and recent commits are good signals of an actively maintained project.
A client is only half of the setup — it needs MCP servers to be useful. Browse our MCP servers directory to find integrations for databases, web search, file systems, and hundreds of APIs, or check our MCP guides and tutorials for step-by-step setup walkthroughs.