Loading video...

Video Failed to Load

Go Home

Anthropic brought Model Context Protocol to life. We gathered 200+ elite hackers for 12 hours to build the open source future of AI agent connections. Here's what we saw at the Finally Connected MCP Hackathon, where LLMs met the real world, with Anthropic, Smithery, Nik Shevchenko, Exa, by Jeremy...

21,172 views • 1 year ago •via X (Twitter)

9 Comments

AGI House SF's profile picture
AGI House SF1 year ago

1/ AutoMCP 🥇 1st Place ToolMaster RL - Training open-source LLMs to excel with MCPs through reinforcement learning. This project creates an environment where models learn tool usage through trial and error rather than prompt engineering. "Reinforcement Learning is All You Need" for transforming mediocre open-source models into tool-using experts that rival closed-source alternatives. Diego Caples, @diegocaples Thomas Joshi, @thomastjoshi Meghna Natraj, @NatrajMeghna Xiangyi Li, @xdotli

AGI House SF's profile picture
AGI House SF1 year ago

2/ MCP Drone 🥈 2nd Place An MCP interface that lets you control drones through natural language commands. Pilot flight patterns, retrieve battery status, and manage drone operations with simple conversational instructions. The perfect demonstration of LLMs merging with the physical world, bringing AI control to the skies. Jake Anderson, @Jandodev Vikram Subbiah, @tiovikram

AGI House SF's profile picture
AGI House SF1 year ago

3/ HomeKit MCP 🥉 3rd Place Your house, controlled by AI. Turn lights on/off, adjust oven temperature, change light colors, and check washing machine status with natural language commands. MCP protocol connected to Apple HomeKit for truly intelligent AI home control. Jacob Zwang, @theshortjacob Will Hopkins, @illothy Ben Swerdlow, @benswerd

AGI House SF's profile picture
AGI House SF1 year ago

4/ Sonauto music model MCP -> News song thing 🥉 3rd Place Music bursting from your AI. An MCP application that transforms depressing headlines into catchy musical performances. Feed it the day's most disheartening news and watch as it converts gloomy content into upbeat songs, ballads, or rap verses. Making staying informed a little less soul-crushing through the power of music and AI creativity. Ryan Tremblay, @zaptrem

AGI House SF's profile picture
AGI House SF1 year ago

5/ nOmi 🥉 3rd Place & Omi Prize Wearable AI companion that captures your words and translates them into digital action. Simply say "Hey Omi, create a GitHub issue" and your MCP agent instantly connects to GitHub and does it for you. Seamlessly bridges your physical experiences with development workflows, making task management effortless wherever inspiration strikes. Sambuddha Basu, @sambuddha_basu Hugo Biais, Akash Sahoo,

AGI House SF's profile picture
AGI House SF1 year ago

6/ ManusMCP AnyLLM Gateway based on Manus - A flexible AGI system that eliminates vibe coding and API key hassles. Seamlessly integrates with your favorite language models, creating a universal interface that works with whatever LLM you prefer. Simple setup, no complicated configuration, just pure AI functionality. Jesse Hu, @huyouare

Greg Caplan 🚀's profile picture
Greg Caplan 🚀2 years ago

Stop wasting time following up with leads. Let our AI agents do it for you.

William Strealy's profile picture
William Strealy1 year ago

@AnthropicAI @SmitheryDotAI It was rad to be a part of this!

barrel of lube's profile picture
barrel of lube1 year ago

@AnthropicAI @SmitheryDotAI Ayy, I could compete for 7th place as well. Invite me next time.

Related 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

142,010 views • 1 year ago