Designing with MCP

Picture this: your AI agents, supercharged with the ability to plug into any tool or knowledge base, just like a USB device boosts your computer’s capabilities. Welcome to the world of the Model Context Protocol (MCP). This revolutionary protocol is set to transform how we build and extend AI agents, making them more adaptable than ever before. In an era where AI evolves at breakneck speed, MCP is the key to keeping your projects ahead of the curve.

What Exactly is MCP?

MCP is like a USB port for AI agents. Just as USB allows you to add peripherals and hard drives to a computer, extending its functionality with ease, MCP enables AI agents to flexibly connect to additional tools and knowledge bases. It acts as a universal cable, standardizing how these components communicate. This plug-and-play approach simplifies the process of enhancing AI capabilities, making it a game-changer for developers and designers alike.

Why MCP Matters

Anthropic developed MCP with the aim of addressing a key problem: AI models often struggle with data isolation, requiring custom connections for each new data source, which slows progress. MCP provides a single, standardized way to connect, making it easier for developers to build and scale AI applications without constant reinvention.

MCP is critical because AI technologies are evolving rapidly. New models, tools like Retrieval-Augmented Generation (RAG), and internal databases emerge constantly, and developers need a way to integrate these advancements without constant overhauls. MCP ensures your work remains extensible and future-proof. For AI agent architecture, it introduces a modular, scalable standard that’s quickly becoming the new norm for connecting agents, tools, and knowledge bases.

MCP in Action

Here’s how MCP amplifies capabilities through real-world examples:

1. Figma to Cursor: Design-Coding Synergy

• MCP server connecting design tools with AI-powered IDEs

• Seamless transfer of design context

• Improved accuracy in design-to-code workflows

Today vibe coders using IDEs like Cursor are not tethered to design tools and patterns leaving creative teams to be subjected to lack of control of the crafting of their digital experiences. This MCP provides a glimpse into how we might craft AI agent teams that can go from design to development in preparation for deployment. A truly end-to-end digital product AI agent team. This MCP is a strong start for teams to explore.

2. Claude to Unity: Game Design Revolution

• Direct communication between LLMs and game engines

• Automated asset generation

• Programmatic control of game development processes

Similar to the Figma MCP workflow, this workflow that includes Unity unlocks AI agents to manipulate and control game engines. Game engines, like Unity, are powerful physics engines that allow for the creation of 3D experiences with realistic physics including: video games, robotics simulation, augmented reality experiences and more. Enabling AI agent interfaces to control the development of Unity-based experiences creates a powerful outlet for developing novel digital experiences.

3. Financial Intelligence Integration

• AI agents accessing real-time market data

• Instant retrieval of financial statements

• Enhanced decision-making capabilities

Understanding stock market data is challenging and traditionally it has cost thousands of dollars and required a background in economics to truly be impactful. Easily connecting a breadth of stock market data to understand macro and micro trends can make for more impactful understanding about market trend data. Today, LLMs like Claude can understand Pine Script data from services like Trading View, but lack a broader context. This MCP adds additional market context to AI agents to support more informed analysis. This MCP highlights how additional knowledge bases like stock market data along with tools such as Pine Script editing can help create a powerful AI agent stock analyst.

MCP Eases Friction Of Deploying Capable AI Agents

MCP unlocks exciting possibilities in building increasingly capable AI agent projects:

1. Quickly prototype bold new feature combinations in hours, not weeks.

2. Test different base language models to optimize performance for your project.

3. Evolve your applications over time by adding new skills or capabilities.

4. Securely integrate user-provided knowledge bases, addressing cybersecurity needs.

5. Build local agent applications for enhanced data security to run inexpensive secure AI agents.

MCP empowers you to innovate faster, adapt smarter, and design with flexibility at the forefront.

The role of MCP in our Technology Experiences

AI agents and AI agent experiences are not meant to replace our existing tech stacks, rather they are augmenting them with newfound capabilities. MCPs are the connections to this existing infrastructure and these new AI agent-based capabilities.

It is not enough to simply connect the infrastructure with MCPs as designers and creative technologists we need to employ systems thinking to envision how our existing human processes can be adapted and our deliverables crafted by adding these new capabilities into our organizations. It is natural for designers to employ systems thinking to consider broader service experiences to strategically adapt experiences to improve performance, a natural extension of this realm is to include synthetic labor as a lever to drive performance and productivity.

Get Started with MCP

Ready to explore MCP?

Dive into this curated list of MCP servers, spanning production-ready tools and experimental projects. Whether you’re enhancing your next design project or coding session, these resources are your entry point to MCP’s potential.

There’s a reason 400,000 professionals read this daily.

Join The AI Report, trusted by 400,000+ professionals at Google, Microsoft, and OpenAI. Get daily insights, tools, and strategies to master practical AI skills that drive results.

Sign up now for free and work smarter, not harder.

💬 Suggestion box

A newsletter exploring the principles that will help us design AI agent experiences and startups that amplify human creativity.

Subscribe to join a community of designers and developers shaping purposeful AI agents.

New Referral Rewards

Until next time, keep innovating and stay curious!

Jason