Загрузка видео...

Не удалось загрузить видео

На главную

Introducing Open MCP Client 🪁 Chat with any MCP server in your own app, just grab a URL from . The team and I vibe coded with Cursor this weekend and built: 1. The first web-based MCP client (link👇) 2. An open-source client you can add into any app...

299,711 просмотров • 1 год назад •via X (Twitter)

Комментарии: 10

Фото профиля Atai Barkai
Atai Barkai1 год назад

Chat with it here: Repo: Docs:

Фото профиля Anmol
Anmol1 год назад

@composiohq Yay! This looks awesome. I'm also trying mcp servers on composio.

Фото профиля Sid Uppal
Sid Uppal1 год назад

Brilliant! Google’s Agents paper differentiates between client-tools and server-tools. If MCP had similar support, that would be the missing piece for enabling CopilotKit to coordinate actions between those that should run in the app and those that should run in the agent.

Фото профиля Atai Barkai
Atai Barkai1 год назад

@composiohq That’s awesome. CopilotKit actually supports full fledged frontend tools (including custom UI etc) so you can actually already do this with the current Open MCP client! Just add frontend actions and they’ll work alongside the MCP ones

Фото профиля Tulsi Soni
Tulsi Soni1 год назад

@composiohq This is amazing! Making it easy to chat with MCP servers in any app is a big step forward. Great work using @CopilotKit, @LangChainAI, and @vercel to build this. Huge shoutout to the team for making it happen! 🚀

Фото профиля Caleb John
Caleb John1 год назад

@composiohq 🔥

Фото профиля Uli 🪁
Uli 🪁1 год назад

@composiohq Team cooked here 🧑‍🍳

Фото профиля elias
elias1 год назад

@composiohq this is neat. looking forward to the day when the auth + connection is baked in so the user doesn't need to go to composio's site. what needs to happen to enable that?

Фото профиля Atai Barkai
Atai Barkai1 год назад

@composiohq Agreed

Фото профиля steve.wasm
steve.wasm1 год назад

better SSE support from -- group your server installs into Profiles and switch them in and out to not overload your context window.

Похожие видео

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,010 просмотров • 1 год назад