Anthropic's New Model Context Protocol in 10 Minutes

--- type: transcript date: 2024-11-25 youtube_id: bpb45HVwwD8 --- # Transcript: Anthropic's New Model Context Protocol in 10 Minutes just today anthropic announced that they're open- sourcing what they're calling model context protocol or mCP for short and they describe this as a new standard for connecting AI assistants to the systems where data lives including content repositories business tools and development environments they describe that it aims to help Frontier models produce better more relevant responses on this video I'll read through the blog post and then I'll point you in the directions on how you can get started with integrating this Within applications they describe as AI assistants gain mainstream adoption the industry has invested heavily in model capabilities achieving rapid advances in reasoning and quality yet even the most sophisticated models are constrained by their isolation from data trapped behind information silos and Legacy systems every new data source requires its own custom implementation making truly connected systems difficult to scale mCP addresses this challenge it provides a universal standard for connecting AI systems with data sources replacing fragmented Integrations with a single protocol the result is simpler more reliable ways to give AI systems access to the data that they need so then they go further to describe the model context protocols now in terms of some of the specifics of the model context protocol they describe that the model context protocol is an open source standard that enables developers to build secure two-way connections between their data sources and AI powered tool tools the architecture is straightforward developers can either expose their data through mCP servers or build AI applications mCP clients that connect to these servers today they're introducing three major components of the model context protocol for Developers for the model context protocol they have sdks with both typescript as well as python right now and you are able to access the local mCP server through the Claud desktop app at time of recording now there's also an open source repository of mCP servers that you can take a look at they describ that cloud 3.5 Sonet is adept at quickly building mCP servers implementations making it easy for organizations and individuals to rapidly connect their most important data sets with a range of AI powered tools to help developers start exploring we're sharing pre-built mCP servers or popular Enterprise systems like Google Drive Slack postgress and Puppeteer early adopters like block and Apollo have integrated mCP into their systems while development tool companies including Zed repet codium and Source graph are working with mCP to enhance their platforms enabling AI agents to better retrieve relevant information to further understand the context around a coding task functional code with fewer attempts at Block open source is more than just a development model it's a foundation of our work and our commitment to creating technology that drives meaningful change and serves as a public good for all open Technologies like the model context provider are the bridge at connecting AI to real world applications ensuring that Innovation is accessible transparent and rooted in collaboration we are excited to partner on a protocol and use it to build agentic systems which removes the burden of the mechanical so people can focus on the creative further they describe that instead of maintaining a separate connection s for each data source developers can now build against a standard protocol as the ecosystem matures AI systems will maintain context as they move between tools and data sets replacing today's fragmented Integrations with a more sustainable architecture developers can start building and testing with mCP connectors today existing Cloud for work customers can begin testing mCP servers locally connecting CLA to internal systems and data sets we'll soon provide a developer toolkit for deploying remote production mCP servers that serve your entire Cloud for work organization now to get started you can install the pre-built mCP servers through the Claud desktop app you can follow the quickart guide to build your first mCP server to contribute to the open source repositories of connectors and implementations you can do so through the link which I'll also put within the description of the video they describe that we're committed to building mCP as a collaborative open source project and ecosystem we're eager to hear your feedback whether you're an AI tool developer an Enterprise looking to leverage existing data or an early adopter exploring the frontier we invite you to build the future of context aware AI together so a pretty interesting announcement now in terms of the protocol itself you can find this on github.com model context protocol and within this there's examples specifications as well as discussion let's just take a look at one of the sdks so for instance the typescript SDK there's an overview which allows applications to provide context for llms in a standardized way separating the concerns of providing context from the actual llm interaction with the SDK this is what you're going to use to build these quote unquote mCP clients that you can connect to mCP servers what the SDK does it allows you to build mCP clients that you can connect to any mCP Server create mCP servers that expose resources prompts and tools use stand transports and then it handles all mCP protocol messages as life cycle events to get started you can just install it and if we take a quick look at the quick start it does look relatively simple to get started you can create the path to your server you can create a new client you can connect to that transport protocol and then you can list out all of the various resources what's great with this is say if you just want to expose to the model what it has access to and what it's capable of you'll be able to do this in more of a general en way out a glance this looks like it will be able to give the models effectively the context of knowing what it's able to accomplish through this mCP protocol it can access things like Puppeteer it will be able to access things like your postgress server and be able to handle all of those different interactions this video is brought to you by scrimba the Innovative coding platform that brings Interactive Learning To Life dive into a variety of courses from AI engineering to frontend python UI design and much more scrim is game changing feature is their unique scrim screencast format which lets you pause the lesson anytime and start directly editing the teachers code their curriculum is built in collaboration with industry leaders including mazilla mdn hugging face and line chain and includes building application with open AI CLA mistal models and guides you on deploying projects to platforms like Cloud flare while AI tools can assist with coding a solid grasp of the fundamentals is essential for achieving real experience scrimba offers something for everyone from complete beginners to Advanced developers and about 80% of scribus content is completely free sign up for a free account today using my link below and enjoy an extra 20% discount on their Pro plans when you're ready to upgrade I'm sure you'll love it now what's going to be interesting with this is how it actually operates and performs with other models within here let's just take a look at the Puppeteer browser automation for inance instance here's an example of Puppeteer which is like a synthetic browser that a lot of people use for web scraping and what have you you can take screenshots navigate web pages execute JavaScript and what have you here's an example of a server that has a variety of different tools you can Puppeteer navigate Puppeteer screenshot Puppeteer click fill basically all of the core components that are built within the Puppeteer Library say if you have an AI agent that does need the capability to navigate the web you could hook it up to one of these types of servers and be able to give it that capability here's just a bit of a deep dive within this you have the specified tools here we see that it's defining the server here and then we're setting up all of the tools that Puppeteer has that it can leverage you can navigate to a URL take a screenshot click on the page fill out an input within the page you can evaluate the JavaScript on the page and then here is the example of the logic of each different function we click what that looks like the screenshot functionality and B basically all of the other cases are all within here effectively how this works is you have the ability to list all the resources that you have within your server it will be able to tell you okay this is a puppeteer server it can take screenshots it can take actions it can navigate to URLs and then you can actually invoke those actions so you can call those requested tools that the llm model that you're using and it will have that ability to understand what the server can do and also actually invoke spoke and utilize that server it's really interesting cuz all of a sudden the llm can just call these servers know what the servers can do and depending on the task or the query it can perform those actions now what's interesting with this is it doesn't necessarily just need to be one server right potentially you'll integrate with multiple different services or have like a Workforce of different examples that you can leverage on interacting with all of these different servers that are out there that have different capabilities obviously a really interesting release and it's going to be interesting to see over the weeks and months following if this starts to get adoption they have a bunch of really great examples but I just wanted to do a quick video pointing you in the direction letting you know about this new model context protocol that's out there let me know your thoughts within the comments are you going to be using this how do you find this better than what we had previously let me know any of your thoughts within the comments below but otherwise if you found this video useful please like comment share and subscribe otherwise until the next one