Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

.Anthropic will support stateless remote MCP servers with “just HTTP” as transport. We’re quite excited about this! So we gave a “lightning talk” at an MCP meetup hosted by Paul Butler Cloudflare Developers yesterday.

100,937 Aufrufe • vor 1 Jahr •via X (Twitter)

11 Kommentare

Profilbild von OpenTools
OpenToolsvor 1 Jahr

It matters because the effort to turn existing REST APIs into more LLM-friendly MCP servers will get that much easier: - No new endpoints required (no /sse) - More options to deploy (serverless)

Profilbild von OpenTools
OpenToolsvor 1 Jahr

(Talk slides are here.)

Profilbild von Eddy Meme
Eddy Memevor 1 Jahr

Looking forward to connecting with you! #eddymeme #CryptoNews #TopNews

Profilbild von matthew k. Daniels
matthew k. Danielsvor 1 Jahr

Hey does every tcp connection have reconnecting sockets so after your opening message there’s a disconnect and TLS wrapper for security? You made it sound like api calls just flying around unprotected. Also could save on compute just delete the poll[] information keep the reconnecting tcp assert

Profilbild von おくの
おくのvor 1 Jahr

@AnthropicAI @paulgb @CloudflareDev i was a little frustrated with that the skinhead guy often failed taking pictures of the screen. I hope he found this post.

Profilbild von Gavin Ching
Gavin Chingvor 1 Jahr

@AnthropicAI @paulgb @CloudflareDev I've been running over websockets on serverless workers on Cloudflare for my users and it definitely works too completely agree though, stateless remote MCP will make it much more simpler

Profilbild von Jad Esber 💥
Jad Esber 💥vor 1 Jahr

@AnthropicAI @paulgb @CloudflareDev Come through:

Profilbild von pelpa.sats | 🟧.pepe
pelpa.sats | 🟧.pepevor 1 Jahr

@AnthropicAI @paulgb @CloudflareDev @KingBootoshi

Profilbild von pelpa.sats | 🟧.pepe
pelpa.sats | 🟧.pepevor 1 Jahr

@AnthropicAI @paulgb @CloudflareDev @grok eli5

Profilbild von ryan yang
ryan yangvor 1 Jahr

@AnthropicAI @paulgb @CloudflareDev http as transport? smart move. integrating new ai into legacy systems often feels like herding cats—stateless mcp servers could tame the chaos. incremental steps > full rewrites. curious how you handle versioning across services without coupling everything too tight?

Profilbild von Rodrigo
Rodrigovor 1 Jahr

@AnthropicAI @paulgb @CloudflareDev Is it Vercel’s triangle? 🤔

Ähnliche Videos

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

141,941 Aufrufe • vor 1 Jahr