Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Anthropic just announced it’s donating MCP to the Linux Foundation, under a new Agentic AI Foundation called ✨AAIF✨, co-founded by Anthropic, OpenAI, and Block. So it’s not just one announcement… it’s actually two … here’s a quick breakdown: 1️⃣ MCP moves to the Linux Foundation MCP launched just a...

lindavivah's profile picture

Linda Vivah (Haviv)

19,434 subscribers

27,874 Aufrufe • vor 10 Monaten •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

18 Kommentare

Profilbild von Qtum
Qtumvor 10 Monaten

This is great news! We've included Model Context Protocol services in Qtum Ally for months now. Nice to see the Linux Foundation involved!

Profilbild von Sree Teja Laveti
Sree Teja Lavetivor 10 Monaten

This is huge! Great announcement

Profilbild von Rishikesh Upadhyay
Rishikesh Upadhyayvor 10 Monaten

This is huge for agentic AI—unifying MCP, Goose, and AGENTS under AAIF feels like the open-source "TCP/IP moment" for multi-agent systems. Can't wait to see how this accelerates interoperable workflows. Thanks for the clear breakdown, Linda! 🚀 What's your first experiment with the new MCP under LF?

Profilbild von Zee
Zeevor 10 Monaten

That’s great

Profilbild von GONZA.
GONZA.vor 10 Monaten

amazing!!!!

Profilbild von Arnav Sharma 🇦🇺
Arnav Sharma 🇦🇺vor 10 Monaten

“Agentic AI Foundation” sounds so majestic for three companies basically agreeing on how to share homework without forking the repo every two weeks.

Profilbild von Prometheus Protocol
Prometheus Protocolvor 10 Monaten

This is massive validation for the open agentic web. MCP standardizes the *handshake*—how an agent connects to a tool. But the critical questions come next: How does the agent *provably trust* that tool? And how does it *pay* for the service? That's the missing infrastructure. We built the on-chain trust and payment rails for exactly this.

Profilbild von TadasG 💻
TadasG 💻vor 10 Monaten

well, MCPs may actually do a comeback now!

Profilbild von Simeon Markoski
Simeon Markoskivor 10 Monaten

That's super interesting, can't wait to see how this impacts the community

Profilbild von This Dot Media
This Dot Mediavor 10 Monaten

Massive news for the ecosystem. MCP is alive and well!

Profilbild von Shreyans Bhansali
Shreyans Bhansalivor 10 Monaten

open source finally getting its marvel crossover moment

Profilbild von Himanshu Kumar
Himanshu Kumarvor 10 Monaten

Linda, this Agentic AI Foundation sounds like a smart move, but will it truly benefit everyone, no?

Profilbild von Juwon AI
Juwon AIvor 10 Monaten

This is a huge step for open AI development. By moving MCP to the Linux Foundation and launching AAIF with OpenAI and Block, we now have a community-governed, vendor-neutral standard for agentic AI. This will accelerate adoption, interoperability, and real-world impact while keeping innovation transparent and collaborative.

Profilbild von Shelton Louis
Shelton Louisvor 10 Monaten

I don't know if this is going to be good! I hope this means models will use MCP's more without nagging! I also hope it gets fixed. The context problem is huge.

Profilbild von Automation | Efficiency | Mindset 🧠
Automation | Efficiency | Mindset 🧠vor 10 Monaten

Open, vendor-neutral MCP under the Linux Foundation. AAIF could become the open standard for agent systems. Linda, what’s the first test you’ll run under AAIF?

Profilbild von Pratap
Pratapvor 10 Monaten

Building on open foundations is how real infrastructure grows 👏 Anthropic, OpenAI, Block - competitors collaborating on shared tools. That's maturity. Linux proved this model scales to the planet 🚀

Profilbild von Karan Jagtiani
Karan Jagtianivor 10 Monaten

Collaboration does open doors, but the challenges of context and interoperability remain. What specific hurdles do you think AAIF will tackle first?

Profilbild von Plain Vanilla (@PlainVanillaPub@Chaos.Social)
Plain Vanilla (@[email protected])vor 10 Monaten

this basically means we get to have that AI-junk on linux, too. thanks, but no thanks.

Ähnliche Videos

Excited to share that I've stepped into a new role as VP of the Agentic AI Foundation (AAIF) 🎉 As AI reshapes our industry, it's critical that this technology evolves in ways that are open and collaborative. Hosted by the Linux Foundation, Agentic AI Foundation is a neutral organization focused on advancing adoption of key open source efforts like MCP, AGENTS.md, and Goose. Our members include Anthropic, OpenAI, Google, AWS, Microsoft, and 100+ others. This work is bigger than any single company or product. I'm ecstatic to help drive AI adoption and interoperability at an industry-wide level.
0:30

Excited to share that I've stepped into a new role as VP of the Agentic AI Foundation (AAIF) 🎉 As AI reshapes our industry, it's critical that this technology evolves in ways that are open and collaborative. Hosted by the Linux Foundation, Agentic AI Foundation is a neutral organization focused on advancing adoption of key open source efforts like MCP, AGENTS.md, and Goose. Our members include Anthropic, OpenAI, Google, AWS, Microsoft, and 100+ others. This work is bigger than any single company or product. I'm ecstatic to help drive AI adoption and interoperability at an industry-wide level.

Angie Jones

76,377 Aufrufe • vor 6 Monaten

MCP is now a part of the Agentic AI Foundation, a directed fund under the Linux Foundation. Co-creator David Soria Parra talks about how a protocol sketched in a London conference room became the open standard for connecting AI to the world—and what comes next for it.
35:31

MCP is now a part of the Agentic AI Foundation, a directed fund under the Linux Foundation. Co-creator David Soria Parra talks about how a protocol sketched in a London conference room became the open standard for connecting AI to the world—and what comes next for it.

Anthropic

72,138 Aufrufe • vor 10 Monaten

Block just open sourced Berd, the desktop app its teams use internally to work with AI agents across projects, skills, tools, and models. "We had access to increasingly capable agents through tools such as Goose, Claude Code, and Codex, but working with them meant navigating different interfaces, configuration systems, and ways of managing context. The technology was powerful, but the experience around it was fragmented." Berd brings conversations, files, instructions, agents, and skills together in one place with persistent projects. Built on top of Goose, the open source agent framework Block contributed to the Agentic AI Foundation under the Linux Foundation. Berd connects to Goose through the Agent Client Protocol, handling the desktop experience while Goose runs the underlying agent loop. Block also recently released Buzz, a separate open source workspace for collaborative agent work. Berd is where you start alone. Buzz is where you go multiplayer.
1:40

Block just open sourced Berd, the desktop app its teams use internally to work with AI agents across projects, skills, tools, and models. "We had access to increasingly capable agents through tools such as Goose, Claude Code, and Codex, but working with them meant navigating different interfaces, configuration systems, and ways of managing context. The technology was powerful, but the experience around it was fragmented." Berd brings conversations, files, instructions, agents, and skills together in one place with persistent projects. Built on top of Goose, the open source agent framework Block contributed to the Agentic AI Foundation under the Linux Foundation. Berd connects to Goose through the Agent Client Protocol, handling the desktop experience while Goose runs the underlying agent loop. Block also recently released Buzz, a separate open source workspace for collaborative agent work. Berd is where you start alone. Buzz is where you go multiplayer.

TFTC

54,922 Aufrufe • vor 1 Monat

It started as a small idea to connect AI models to developer workflows. It turned into one of the fastest-growing open standards in the industry. 🚀 Now, the Model Context Protocol is officially joining the The Linux Foundation. Hear from the engineers and maintainers of GitHub, Microsoft, Anthropic, and OpenAI on the journey from day zero to now. 👇
1:36

It started as a small idea to connect AI models to developer workflows. It turned into one of the fastest-growing open standards in the industry. 🚀 Now, the Model Context Protocol is officially joining the The Linux Foundation. Hear from the engineers and maintainers of GitHub, Microsoft, Anthropic, and OpenAI on the journey from day zero to now. 👇

GitHub

45,059 Aufrufe • vor 10 Monaten

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!
2:43

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

142,256 Aufrufe • vor 1 Jahr

wtf is MCP? Paul Klein IV, CEO of explains "Model Context Protocol" (MCP) in plain terms: "There's this new way that people are exposing tools to AI & the 'Model Context Protocol' is one of those ways that you can standardize & give your AI a set of tools to call. BrowserBase has a way to expose the browser to your agent via MCP or MCP server. More & more developers are trying to find ways to integrate more functionalities to their AI agents & BrowserBase's browsers are one of those primitive functionalities, & the MCP is just one way to integrate it into your software." Paul Klein IV From 🅱️'s GitHub: Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you’re building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need. This server provides cloud browser automation capabilities using Browserbase and Stagehand. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a cloud browser environment.
0:40

wtf is MCP? Paul Klein IV, CEO of explains "Model Context Protocol" (MCP) in plain terms: "There's this new way that people are exposing tools to AI & the 'Model Context Protocol' is one of those ways that you can standardize & give your AI a set of tools to call. BrowserBase has a way to expose the browser to your agent via MCP or MCP server. More & more developers are trying to find ways to integrate more functionalities to their AI agents & BrowserBase's browsers are one of those primitive functionalities, & the MCP is just one way to integrate it into your software." Paul Klein IV From 🅱️'s GitHub: Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you’re building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need. This server provides cloud browser automation capabilities using Browserbase and Stagehand. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a cloud browser environment.

Molly O’Shea

20,408 Aufrufe • vor 1 Jahr

Gilbert Verdian (CEO of ) said it best: “We are on the journey to create a new internet the internet of trust.” Blockchain isn’t just about crypto. It’s about rebuilding the internet’s foundation. $QNT is building that foundation quietly, powerfully, and globally.
0:51

Gilbert Verdian (CEO of ) said it best: “We are on the journey to create a new internet the internet of trust.” Blockchain isn’t just about crypto. It’s about rebuilding the internet’s foundation. $QNT is building that foundation quietly, powerfully, and globally.

Merlijn The Trader

46,987 Aufrufe • vor 1 Jahr

Nick Freitas just told me that a spiritual revival is “essential to the revival of Western civilization.” “Western civilization didn’t just appear out of the ether.” “It’s not a result of secular humanism.” “It is built upon a foundation of Christian moral teaching and Christian thought.” “The most common thing quoted by the Founders of our country was the Bible.” “Christianity actually provides… a foundation for objective truth and objective morality.” Nick Freitas
1:34

Nick Freitas just told me that a spiritual revival is “essential to the revival of Western civilization.” “Western civilization didn’t just appear out of the ether.” “It’s not a result of secular humanism.” “It is built upon a foundation of Christian moral teaching and Christian thought.” “The most common thing quoted by the Founders of our country was the Bible.” “Christianity actually provides… a foundation for objective truth and objective morality.” Nick Freitas

Jan Jekielek

11,355 Aufrufe • vor 3 Monaten

🚀The ChainOpera MCP Servers are live. This isn’t just another node on a network—this is a step toward decentralizing OpenAI itself. Owned. Operated. Coordinated. By you. Today’s MCP launch gives anyone the power to run and sync agent-based AI models across a mesh of independent compute. It’s messy. It’s raw. It’s real. But it works. This is the infrastructure layer OpenAI never built. Because decentralized AGI won’t come from one lab—it’ll emerge from protocols, not platforms. We’re not launching a product feature. We’re bootstrapping a movement. Test it. Break it. Tell us everything. Your feedback = better infra. Your ideas = better AI. Your participation = ownership. Tag ChainOpera AI . Share your logs, crashes, experiments. Let’s co-create Decentralized OpenAI — together. #BTC #BNB #OpenAI #ChainOpera #ETH #SOL #MCP
1:41

🚀The ChainOpera MCP Servers are live. This isn’t just another node on a network—this is a step toward decentralizing OpenAI itself. Owned. Operated. Coordinated. By you. Today’s MCP launch gives anyone the power to run and sync agent-based AI models across a mesh of independent compute. It’s messy. It’s raw. It’s real. But it works. This is the infrastructure layer OpenAI never built. Because decentralized AGI won’t come from one lab—it’ll emerge from protocols, not platforms. We’re not launching a product feature. We’re bootstrapping a movement. Test it. Break it. Tell us everything. Your feedback = better infra. Your ideas = better AI. Your participation = ownership. Tag ChainOpera AI . Share your logs, crashes, experiments. Let’s co-create Decentralized OpenAI — together. #BTC #BNB #OpenAI #ChainOpera #ETH #SOL #MCP

ChainOpera AI

10,173 Aufrufe • vor 1 Jahr

We’re proud to present our latest creation, a bold reflection of our #mission and #vision. At the heart of everything we do lies a commitment to clean energy, intelligent infrastructure, and a future shaped by #nature. But this isn’t just about #energy. It’s about laying the foundation for a new digital era. One where #blockchain, #AI, and green infrastructure work in harmony. This is more than technology. It’s purpose. It’s progress. It’s tomorrow.
0:49

We’re proud to present our latest creation, a bold reflection of our #mission and #vision. At the heart of everything we do lies a commitment to clean energy, intelligent infrastructure, and a future shaped by #nature. But this isn’t just about #energy. It’s about laying the foundation for a new digital era. One where #blockchain, #AI, and green infrastructure work in harmony. This is more than technology. It’s purpose. It’s progress. It’s tomorrow.

Hearst

19,193 Aufrufe • vor 1 Jahr

Today, we're supporting MCP in Flowise! There has been a lot of discussion about MCP lately. From our perspective, MCP is nothing fancy - just tools with third-party APIs or functions, wrapped under a unified protocol that can be consumed by client LLM applications. In fact, we've had something similar for a long time with Langchain Tools. However, MCP offers two key benefits: - Its open protocol isn’t limited to specific frameworks - Client applications (like us, Cursor , @windsurf , etc) can offload the burden of maintaining and updating these tools to the official MCP creators These MCP servers (a.k.a. tools) are provided to the LLM, allowing it to decide when and how to use them. This is sometimes referred to as an "agentic" approach, as opposed to a "deterministic" approach like Zapier, where each step must be explicitly mapped out. In real-world scenarios, you might find yourself needing both approaches depending on the use case. It's still early days, and it will take time for the community to establish standards. We're excited to see where this goes!
0:46

Today, we're supporting MCP in Flowise! There has been a lot of discussion about MCP lately. From our perspective, MCP is nothing fancy - just tools with third-party APIs or functions, wrapped under a unified protocol that can be consumed by client LLM applications. In fact, we've had something similar for a long time with Langchain Tools. However, MCP offers two key benefits: - Its open protocol isn’t limited to specific frameworks - Client applications (like us, Cursor , @windsurf , etc) can offload the burden of maintaining and updating these tools to the official MCP creators These MCP servers (a.k.a. tools) are provided to the LLM, allowing it to decide when and how to use them. This is sometimes referred to as an "agentic" approach, as opposed to a "deterministic" approach like Zapier, where each step must be explicitly mapped out. In real-world scenarios, you might find yourself needing both approaches depending on the use case. It's still early days, and it will take time for the community to establish standards. We're excited to see where this goes!

FlowiseAI

27,415 Aufrufe • vor 1 Jahr

Base just launched something that changes how AI agents interact with blockchain. It's called Base MCP. Here's what it actually does 🧵 Base MCP is an open-source MCP server built by Coinbase for the Base network. It connects AI clients, Claude, ChatGPT, to Base Network. You type a natural language prompt. The agent prepares the transaction. You approve it. Done. Your keys never touch the server. Nothing moves on-chain without your explicit sign-off. you can use it to Track portfolio balances across Base and any Base Account supported EVM chain. View transaction history. Send funds Swap tokens Use supported apps and protocols on Base through skill plugins Pay for x402 enabled services To test it, I connected it to BlockLottery, an on-chain lottery protocol with NFT tickets and VRF-powered draws. Two questions to the agent: → "What lotteries are open right now?" Queried the factory contract. Matched the partner dashboard exactly. → "Check this wallet's portfolio." Scanned the chain, handled RPC limits, returned a clean breakdown. Spot on. This is what crypto-native AI tooling looks like. Not hype. An actual working MCP server, launched May 26, 2026. Base MCP docs: BlockLottery: Base Build Base #blockchain #AI #Web3
2:40

Base just launched something that changes how AI agents interact with blockchain. It's called Base MCP. Here's what it actually does 🧵 Base MCP is an open-source MCP server built by Coinbase for the Base network. It connects AI clients, Claude, ChatGPT, to Base Network. You type a natural language prompt. The agent prepares the transaction. You approve it. Done. Your keys never touch the server. Nothing moves on-chain without your explicit sign-off. you can use it to Track portfolio balances across Base and any Base Account supported EVM chain. View transaction history. Send funds Swap tokens Use supported apps and protocols on Base through skill plugins Pay for x402 enabled services To test it, I connected it to BlockLottery, an on-chain lottery protocol with NFT tickets and VRF-powered draws. Two questions to the agent: → "What lotteries are open right now?" Queried the factory contract. Matched the partner dashboard exactly. → "Check this wallet's portfolio." Scanned the chain, handled RPC limits, returned a clean breakdown. Spot on. This is what crypto-native AI tooling looks like. Not hype. An actual working MCP server, launched May 26, 2026. Base MCP docs: BlockLottery: Base Build Base #blockchain #AI #Web3

BlockLottery

11,671 Aufrufe • vor 4 Monaten

Which coding agent is right for you? 🤔 This question poses a major challenge to developers and teams. That's why we’re launching the Developer Productivity AI Arena, an open-source platform that will allow the community to benchmark, rank, and contribute datasets – and hopefully bring about a collective solution to this shared problem. JetBrains intends to contribute the project to the Linux Foundation for transparent governance. 🔗 Learn more and see how to get involved:
1:01

Which coding agent is right for you? 🤔 This question poses a major challenge to developers and teams. That's why we’re launching the Developer Productivity AI Arena, an open-source platform that will allow the community to benchmark, rank, and contribute datasets – and hopefully bring about a collective solution to this shared problem. JetBrains intends to contribute the project to the Linux Foundation for transparent governance. 🔗 Learn more and see how to get involved:

JetBrains

16,748 Aufrufe • vor 11 Monaten

AI without human intelligence is incomplete. That’s why OptimAI is building DeHIN (Decentralized Human Intelligence Network), where community knowledge, insights, and expertise shape the foundation of tomorrow’s Agentic AI Systems. 👉 💡 Your domain knowledge isn’t just valuable - it’s essential. Together, we validate truths, filter noise, and make AI more authentic, trustworthy, and human. ⚡ And here’s the exciting part: The upcoming release of the OptimAI Core Node will introduce our Data Validation Protocol. This means YOU - the OptimAI community, can directly contribute to validating data, shaping better AI, and earning greater rewards for creating real-world impact. This isn’t just participation. It’s co-creating the future of Agentic AI. A future Built for the People, by the People. Stay tuned. Together We BUIDL!
0:40

AI without human intelligence is incomplete. That’s why OptimAI is building DeHIN (Decentralized Human Intelligence Network), where community knowledge, insights, and expertise shape the foundation of tomorrow’s Agentic AI Systems. 👉 💡 Your domain knowledge isn’t just valuable - it’s essential. Together, we validate truths, filter noise, and make AI more authentic, trustworthy, and human. ⚡ And here’s the exciting part: The upcoming release of the OptimAI Core Node will introduce our Data Validation Protocol. This means YOU - the OptimAI community, can directly contribute to validating data, shaping better AI, and earning greater rewards for creating real-world impact. This isn’t just participation. It’s co-creating the future of Agentic AI. A future Built for the People, by the People. Stay tuned. Together We BUIDL!

OptimAI Network

42,066 Aufrufe • vor 1 Jahr

You are brain-dead if you think the CLI killed MCP. Anthropic just reported 300 million downloads for the MCP SDK (up from 100M at the beginning of the year). The complaint I keep hearing: MCP pollutes your context. That's a 1-year-old argument. Context pollution is not a protocol problem, but a client one. None of the agentic tools you use have that issue: Claude Code, Codex, Cursor, etc. All of them implement progressive disclosure and load MCP tools on demand. MCPs and CLIs complement each other: • MCP offers OAuth-based authentication, standardized transport, remote access for cloud-hosted agents, and a public registry with thousands of servers. • CLIs offer Unix-style composition (pipes, stdin/stdout), zero upfront schema cost, and massive training distribution (models have seen far more shell than any structured tool format). You don't (and shouldn't) pick a side here. You should be using both where they fit.
6:21

You are brain-dead if you think the CLI killed MCP. Anthropic just reported 300 million downloads for the MCP SDK (up from 100M at the beginning of the year). The complaint I keep hearing: MCP pollutes your context. That's a 1-year-old argument. Context pollution is not a protocol problem, but a client one. None of the agentic tools you use have that issue: Claude Code, Codex, Cursor, etc. All of them implement progressive disclosure and load MCP tools on demand. MCPs and CLIs complement each other: • MCP offers OAuth-based authentication, standardized transport, remote access for cloud-hosted agents, and a public registry with thousands of servers. • CLIs offer Unix-style composition (pipes, stdin/stdout), zero upfront schema cost, and massive training distribution (models have seen far more shell than any structured tool format). You don't (and shouldn't) pick a side here. You should be using both where they fit.

Santiago

68,929 Aufrufe • vor 5 Monaten

new chapter begins: a terminal for the agentic future, built on blockchain, powered by AI. This is our marketplace—a glimpse of what AGI will mean for crypto. Today, we launch 3 agents—Image Generation, Token Swap Agent, & Blockchain Tax Estimate Agent—out of hundreds to come. We see an agentic future where AI guides every step: buying online, managing finances, transacting globally. FOMO’s here to make that real, with experts at your side. Our Model Context Protocol (MCP) ties it together—agents talking, reasoning, scaling across crypto and DeFi. It’s orchestration with a brain, evolving daily. FOMO’s not just building tools; we’re pushing intelligent automation into blockchain’s core. Our Model Context Protocol (MCP) is the backbone. Think of it as a conductor for AI agents—each runs its own logic (workflows, API calls, LLMs), but MCP syncs them on-chain. Agents share context via a lightweight event bus, logged to a blockchain ledger. Agent A (say, Market Analysis) pulls stock data, flags trends. Agent B (Email Sales) reads that, drafts outreach—both talk through MCP’s orchestration layer. We use Web3 hooks to settle fees or split revenue, all transparent. It’s messy, but it scales. Under the hood: MCP leans on a pub-sub model—agents publish tasks, others subscribe. We’re training them with RL loops to optimize gas costs and response times. Goal? A self-tuning swarm of agents reasoning over DeFi, NFTs, whatever’s next. This is FOMO’s bet on AGI. Welcome to the new FOMO. We’re not just building tools—we’re wiring AI into crypto’s future, agent by agent. A leader in blockchain intelligence, starting here. Join us as we push the boundaries.
1:16

new chapter begins: a terminal for the agentic future, built on blockchain, powered by AI. This is our marketplace—a glimpse of what AGI will mean for crypto. Today, we launch 3 agents—Image Generation, Token Swap Agent, & Blockchain Tax Estimate Agent—out of hundreds to come. We see an agentic future where AI guides every step: buying online, managing finances, transacting globally. FOMO’s here to make that real, with experts at your side. Our Model Context Protocol (MCP) ties it together—agents talking, reasoning, scaling across crypto and DeFi. It’s orchestration with a brain, evolving daily. FOMO’s not just building tools; we’re pushing intelligent automation into blockchain’s core. Our Model Context Protocol (MCP) is the backbone. Think of it as a conductor for AI agents—each runs its own logic (workflows, API calls, LLMs), but MCP syncs them on-chain. Agents share context via a lightweight event bus, logged to a blockchain ledger. Agent A (say, Market Analysis) pulls stock data, flags trends. Agent B (Email Sales) reads that, drafts outreach—both talk through MCP’s orchestration layer. We use Web3 hooks to settle fees or split revenue, all transparent. It’s messy, but it scales. Under the hood: MCP leans on a pub-sub model—agents publish tasks, others subscribe. We’re training them with RL loops to optimize gas costs and response times. Goal? A self-tuning swarm of agents reasoning over DeFi, NFTs, whatever’s next. This is FOMO’s bet on AGI. Welcome to the new FOMO. We’re not just building tools—we’re wiring AI into crypto’s future, agent by agent. A leader in blockchain intelligence, starting here. Join us as we push the boundaries.

FOMO

26,338 Aufrufe • vor 1 Jahr

Martin Keen from IBM just explained the debate that's splitting Claude and AI agent developers in half CLI vs MCP - and the answer will save you thousands of tokens > GitHub MCP server loads 80 tools into context = 55,000 tokens before your agent does anything > CLI: agent already knows grep, cat, git cold from training data > MCP wins when Claude needs to render a JavaScript page - curl can't do that, MCP browser server can in 250 tokens > MCP wins for Slack, Notion, databases - OAuth handled by the server, not the agent the rule: use CLI when commands map directly to the job, use MCP when the abstraction earns its cost full breakdown above
13:25

Martin Keen from IBM just explained the debate that's splitting Claude and AI agent developers in half CLI vs MCP - and the answer will save you thousands of tokens > GitHub MCP server loads 80 tools into context = 55,000 tokens before your agent does anything > CLI: agent already knows grep, cat, git cold from training data > MCP wins when Claude needs to render a JavaScript page - curl can't do that, MCP browser server can in 250 tokens > MCP wins for Slack, Notion, databases - OAuth handled by the server, not the agent the rule: use CLI when commands map directly to the job, use MCP when the abstraction earns its cost full breakdown above

Mr. Buzzoni

40,771 Aufrufe • vor 4 Monaten

THE x402 META IS HERE BUT $SUI's ALREADY LOCKED IN A SEAT AT GOOGLE’S TABLE 👀 AP2 is Google's Agent Payments Protocol, built for autonomous, machine-to-machine payments Over 60 organizations are contributing to the standard Only a handful are blockchains Sui is one of them 💯 It supports atomic, conditional payments with secure routing between digital agents The kind of architecture Sui was built to handle It’s open-source, donated to the Linux Foundation, and aimed at powering agentic commerce across AI, IoT, and Web3 From object-based design to composability and high throughput, Sui’s stack is aligned with the needs of real-time, autonomous commerce This is a credibility unlock. It anchors Sui to a real-world protocol backed by one of the most powerful players in AI and cloud infrastructure It's also an ecosystem opportunity Developers can now explore AP2-integrated use cases on Sui: agent-led payments, decentralized marketplaces, IoT transactions That leads to usage Which drives utility Which fuels $SUI There's still a lot to build But the alignment is no longer speculative Google picked Sui to help shape the standard Watch what that unlocks
0:51

THE x402 META IS HERE BUT $SUI's ALREADY LOCKED IN A SEAT AT GOOGLE’S TABLE 👀 AP2 is Google's Agent Payments Protocol, built for autonomous, machine-to-machine payments Over 60 organizations are contributing to the standard Only a handful are blockchains Sui is one of them 💯 It supports atomic, conditional payments with secure routing between digital agents The kind of architecture Sui was built to handle It’s open-source, donated to the Linux Foundation, and aimed at powering agentic commerce across AI, IoT, and Web3 From object-based design to composability and high throughput, Sui’s stack is aligned with the needs of real-time, autonomous commerce This is a credibility unlock. It anchors Sui to a real-world protocol backed by one of the most powerful players in AI and cloud infrastructure It's also an ecosystem opportunity Developers can now explore AP2-integrated use cases on Sui: agent-led payments, decentralized marketplaces, IoT transactions That leads to usage Which drives utility Which fuels $SUI There's still a lot to build But the alignment is no longer speculative Google picked Sui to help shape the standard Watch what that unlocks

eye zen hour 🥶

13,230 Aufrufe • vor 11 Monaten