Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Recently Cloudflare released a new way to build remote MCP servers, with the help of their platform and Durable Objects. Advantages ? woah chef's kiss - Authentication and Authorization built into your MCP (awesome for web3 use cases!) - Remote (SSE) - Accesible with WEB clients (woah) Understand better...

55,370 görüntüleme • 1 yıl önce •via X (Twitter)

11 Yorum

terminus profil fotoğrafı
terminus1 yıl önce

MCP servers are a match made in heaven for Web3. Open protocol paired with internet capital markets, bringing you permissionless finance wherever you go. Blocker ? MCP servers has been largely local only with specific local only client interactions. Meaning, you'd have to download specific code, to load into a local client like Claude desktop/cursor to have any sort of interaction with that MCP. This leaves MCP to only very technical people and the barrier to entry is very high.

terminus profil fotoğrafı
terminus1 yıl önce

How is this great for web3 and specifically @solana ? In the demo example that we built in the video, its a scrappy multisig system whereby you give access to your backend system a keypair where you can load tokens (think of it like a warm wallet). It's a 2/2 multisig system, and the other signature is your mobile wallet. send sol to anyone by approving txns from your mobile wallet without having the funds in your wallet. ofc, this can be improved with a 2/3 system or even a proper multisig from @SquadsProtocol

terminus profil fotoğrafı
terminus1 yıl önce

This is a great use case for a remote MCP server, but you get the point. From here teams can easily build MCP servers accessible to anyone with just a mobile wallet! We think this is Blinks supercharged! -think @JupiterExchange MCP -lulo MCP etc All @solana or @aeyakovenko has to do is build an official WEB BASED MCP client that lets anyone input in their domain (.com what have you) and have users interact with your MCP in seconds! lost? just try it out! Links are in the next tweet!

terminus profil fotoğrafı
terminus1 yıl önce

Demo Remote MCP server by Terminus : Web based MCP client by Cloudflare : Docs on building Remote MCP servers : shoutout to the awesome team at @Cloudflare for building this, thank you! @dinasaur_404 @threepointone

terminus profil fotoğrafı
terminus1 yıl önce

for visibility please @aeyakovenko not a scam, this is good for @solana @sendaifun @rajgokal Jupiter is kinda like the frontpage of @solana in some ways. Mark our words, the next breakout app on @solana will be a web based MCP client that anyone can use, friendly good UI/UX. We think that Clients are sticky while tools and MCP servers are not. Think of App stores vs individual apps.

terminus profil fotoğrafı
terminus1 yıl önce

how to try it? - go to cloudflare's playground in the link above - paste the server url and connect. interact with the mcp by saying 'help me send {solamount} to {recipient public key}' scan the QR code for results with @phantom wallet. its a solana pay QR code. todo - if server is sensitive add specifc auth/authorizations - add more tools the age of .com everyone had a website. soon everyone will have a remote mcp server (think of it like email?)

Houdini profil fotoğrafı
Houdini1 yıl önce

@Cloudflare It takes so much command typing it. You should be able to sit down and synthesize another way making buying, sending and selling easy for Web3 and Web2 users. When building makes a list on what makes you better than a sniper bot or what gives you an edge over it

terminus profil fotoğrafı
terminus1 yıl önce

Thank you for the feedback! agree on this When building make a list on what makes you better than a sniper bot or what gives you an edge over it

Lui profil fotoğrafı
Lui1 yıl önce

@Cloudflare $Terminus

JF profil fotoğrafı
JF1 yıl önce

@Cloudflare @aeyakovenko 👀

RTTS profil fotoğrafı
RTTS2 yıl önce

API testing of interfaces is critical to determine if they meet requirements for functionality, reliability, performance, and security. Check out RTTS - the automated testing experts since 1996. #API #testautomation #integrationtest

Benzer Videolar

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

142,130 görüntüleme • 1 yıl önce