Empowering AI Agents with Tools using MCP

AI chatbots respond to prompts, but AI agents are much more interesting because they can take meaningful action on your behalf when you empower them with tools. In this talk we explain the concept of a tool and show how to allow an AI agent tool access through the emerging Model Context Protocol (MCP) standard. We will also survey the growing marketplace of MCP servers and how you can integrate them. Finally, we will consider how you can expose your own functionality through the MCP server standard.

By the end of this talk you should understand what tools are, why AI agents benefit from them, what role MCP plays, what problems it solves, when to use it, and how to create your own MCP-compatible tool.

Agents Don’t Click Ads: Pay-by-the-Drink with MCP and x402

In June 2026, Cloudflare reported automated web traffic had overtaken human traffic, driven in part by the explosive growth of AI agents. HUMAN Security’s 2026 benchmark report found that agentic AI traffic grew 7,851% in one year. Our future is more agents. Since agents don't read ads or subscribe to services the way humans do, how will we monetize the increasingly agent-powered web?

The Model Context Protocol (MCP) has emerged as a cross-platform protocol to empower agents to access data and tools. If you have valuable data or functionality, exposing it as an MCP tool is now an established approach to making it accessible to agents. But how do you get paid? Traditional accounts, API keys, and billing relationships introduce friction for agents that want to purchase a service on demand. The x402 payment protocol comes to the rescue, enabling payments via cryptocurrency (USDC in this scenario) with no account and no API key.

In this fast-paced talk, we will briefly review the role and history of MCP, contrasting it with WebMCP, APIs, and CLIs for agent use. Then we'll show how to weave in the x402 protocol to expose an MCP tool to the world that you can charge for, but without requiring an account or API key.

Our example is real. Since January 1, 2022, I’ve co-run the Attackee Project, a honeypot that has logged tens of millions of attempts to break into our systems. We’ll turn that data into a new premium feature on the ipfacts.com MCP server: check whether an IP address is on our "naughty list" (i.e., tried to log into our honeypot), and agents pay per call (in USDC) via x402.

You’ll walk away knowing when MCP is the right choice for agent access, and see the x402 pattern for charging agents per call.

Human Language is the New UI: How This Is Possible

Remember the first time you typed a question into ChatGPT and it responded with an answer so clear it seemed like a human wrote it? This was an eye-opening moment. This ability to understand and generate language was vastly more effective than anything we'd seen before.

This breakthrough in language understanding propelled ChatGPT to an unprecedented 100 million users in just two months, the fastest adoption of any application in history.

This language understanding is fueling a change in human-computer interaction, powering everything from chatbots to AI Agents. It's why Microsoft CEO Satya Nadella says, 'Human language is the new UI layer.' But how is this possible?

But how is this possible?

This talk will give you a practical look at how human language can be converted into a mathematical representation. We'll develop an intuitive understanding, starting with a brief introduction to tokens and embedding models. This will build to the idea of "semantic" representation, which is a core concept. We won't go deep on the math, but rather we’ll focus on how vectors are used to represent the meaning of words and how we can calculate the similarity between them.

From Theory to Practice: Language Understanding in Action

Though language understanding is also part of Large Language Models (LLMs), we will see semantic representation isolated in a purpose-built web app that lets you interactively compare text snippets side-by-side to see their semantic similarity. You'll be able to try it yourself and see how it works across different human languages and even programming languages.

Then we'll take a peek inside Microsoft AI Foundry to show an example of where you can find the technology used by the web app.

We’ll close by connecting the dots to other popular AI and AI-adjacent technologies like semantic search, vector databases, retrieval augmented generation (RAG), coding assistants, and even the humble chatbot. Don’t worry if any of these terms are unfamiliar. We’ll focus on how the language understanding piece is relevant. This can help you appreciate when these other technologies might be useful.

Target Audience

This talk is for any curious student. If you've used ChatGPT (or a similar tool), you're ready for this talk; no other technical background is required.

Takeaways

You'll walk away with a clearer idea of how human language can be the new UI layer and how you can make use of that understanding.

Student-targeted version