发现优秀的 MCP 服务器与客户端
MCP.so 是一个第三方 MCP 市场,收录了 22813 个 MCP 服务器。
ShipAny: NextJS boilerplate for building AI SaaS startups.
精选 MCP Client(MCP 客户端)
查看全部HyperChat
HyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.
Y Gui
A web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
DeepChat
Your AI Partner on Desktop
Cherry Studio
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
Visual Studio Code - Open Source ("Code - OSS")
Visual Studio Code
Continue
⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks
A Sleek AI Assistant & MCP Client
5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .
y-cli 🚀
A Tiny Terminal Chat App for AI Models with MCP Client Support
Cline – #1 on OpenRouter
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
Cursor
The AI Code Editor
ChatWise
The second fastest AI chatbot™
Windsurf
The new purpose-built IDE to harness magic
最新 MCP Client(MCP 客户端)
查看全部MCP Peek
MCP Peek is a local-first desktop app to inspect, run, and proxy MCP servers. Connect any server over stdio or HTTP/SSE, browse its full catalog of tools, resources, and prompts with token-cost estimates, run tools through auto-generated forms, and capture live request/response traffic with the built-in proxy.
Atomic Chat
Private, free, open-source local AI chat and MCP host. Run 1000+ LLMs on your device, connect any MCP server (STDIO, HTTP, SSE) and use tools with local or cloud models - no cloud API required
OMNFLOW
Omnflow is an AI-powered content repurposing tool built for creators, marketers, and founders who publish across multiple platforms. The Omnflow MCP server gives Claude three powerful tools: repurpose_content Turn any blog post, newsletter, transcript, podcast notes, or rough idea into 5 platform-ready posts — LinkedIn, Twitter/X, Instagram, Facebook, and more. Maintains your tone and style automatically. analyze_voice Extract your unique Voice DNA from any writing sample. Captures tone, sentence structure, vocabulary patterns, and writing style so every repurposed post sounds authentically like you. list_recent_demos Browse your recent repurposing runs — source inputs and generated outputs — without leaving Claude. Who it's for: Content creators publishing across multiple platforms Founders doing build-in-public content Marketers turning long-form content into social posts Newsletters writers repurposing issues into social content Connect via: https://omnflow.com/api/mcp
ADSUMO - #1 MCP for ad creatives
Adsumo turns any MCP-compatible AI tool into an ad studio. Connect once and your assistant can create professional, on-brand image and video ads without design tools or manual exports. Onboard a brand from a URL and Adsumo learns its logo, colors, voice, and products, so every ad comes out on-brand automatically. From there you can generate batches of image ads, produce video ads with Sora, Veo, Kling, or Seedance, edit and reframe creatives for any placement, translate copy into 100+ languages, and research what is winning in your niche through the built-in ad library. Run a single prompt or fire a full launch campaign across formats in one chat. *Some features require a subscription
常见问题
关于 MCP 服务器的常见问题
什么是 MCP(模型上下文协议)?
MCP 是由 Anthropic 开发的开源协议,使 Claude 等 AI 系统能够安全地连接各种数据源。它通过客户端-服务器架构为 AI 助手提供了访问外部数据、工具和提示的通用标准。
什么是 MCP 服务器?
MCP 服务器是为 AI 客户端提供上下文、工具和提示的系统。它们可以暴露文件、文档、数据库和 API 集成等数据源,使 AI 助手能够以安全的方式访问实时信息。
MCP 服务器是如何工作的?
MCP 服务器通过简单的客户端-服务器架构工作。它们通过标准化协议暴露数据和工具,在 Claude Desktop 等主机应用程序内部与客户端保持安全的一对一连接。
MCP 服务器能提供什么?
MCP 服务器可以共享资源(文件、文档、数据)、暴露工具(API 集成、操作)并提供提示(模板化交互)。它们控制自己的资源并维护清晰的系统边界以确保安全。
Claude 如何使用 MCP?
Claude 可以连接到 MCP 服务器以访问外部数据源和工具,通过实时信息增强其功能。目前,这适用于本地 MCP 服务器,企业远程服务器支持即将推出。
MCP 服务器安全吗?
是的,安全性已内置于 MCP 协议中。服务器控制自己的资源,无需与 LLM 提供商共享 API 密钥,系统保持清晰的边界。每个服务器管理自己的身份验证和访问控制。
什么是 mcp.so?
mcp.so 是一个社区驱动的平台,收集和组织第三方 MCP 服务器。它作为一个中心目录,用户可以在这里发现、分享和了解可用于 AI 应用程序的各种 MCP 服务器。
如何将我的 MCP 服务器提交到 mcp.so?
您可以通过在我们的 GitHub 仓库中创建新的 issue 来提交您的 MCP 服务器。点击导航栏中的"提交"按钮或直接访问我们的 GitHub issues 页面。请提供有关您的服务器的详细信息,包括名称、描述、功能和连接信息。
探索 MCP 服务器
从这里开始发现优秀的 MCP 服务器。