All posts
Product design

What Is MCP? A Plain-English Guide for Designers and Founders

What is MCP? A plain-English guide to the Model Context Protocol: hosts, clients, servers and tools, with an agent reading a Figma file or a CMS.

By Mehdi Hassan4 min read

The short answer

MCP, the Model Context Protocol, is an open standard that lets AI apps connect to outside tools and data through one common plug. A server wraps a product such as Figma or a CMS, a client inside the AI app talks to it, and the model can then read files or take actions without a custom integration for every app.

Key takeaways

  • MCP is a shared plug between AI apps and products, so each product builds one server instead of many integrations.
  • Servers offer three things: tools the model can call, resources it can read and prompts users can pick.
  • MCP doesn't replace APIs: most servers sit on top of a product's existing API.
  • For designers, MCP is how an agent reads a Figma frame's structure and variables, not just a screenshot.
  • The user still grants access and approves tool calls, so permission design matters as much as the protocol.

Part of AI Product UX: How to Design AI Features Users Trust

What is MCP in plain English?

MCP is a standard way for an AI assistant to plug into other software. Instead of every AI app writing its own connector to every product, a product publishes one MCP server, and any AI app that speaks MCP can use it.

Think of it as a universal port. Each product exposes its features once, in the same format, and the assistant discovers what it can do. Anthropic introduced it as an open protocol, with the specification at modelcontextprotocol.io. It sits underneath much of our hub on AI product UX, because it's how chat and agent features reach real data.

How do MCP servers, clients and hosts work?

MCP has three roles. The host is the AI app you use, such as a chat app or a coding editor. Inside it, a client keeps a connection to each server, and each server wraps one product or data source.

In the official specification, a server can offer three kinds of features:

  • Tools: actions the model can call, such as "create a page" or "get this frame".
  • Resources: data the model can read as context, such as documents or records.
  • Prompts: ready-made templates a user can choose, such as "summarize this file".

Servers run locally or remotely, and remote servers usually ask you to sign in, so the agent acts with your account's access. The spec says hosts must get user consent before a tool runs, and it's revised in dated versions, so check modelcontextprotocol.io for current details. Our AI infrastructure industry page shows how we explain products like this.

How does MCP compare to APIs and plugins?

MCP doesn't replace an API. Most MCP servers are a thin layer over a product's existing API, describing its actions so a model can discover and call them. A plugin is usually built for one specific app.

Term

Who uses it

What it does

API

Developers writing code

Exposes a product's data and actions to programs

Plugin or extension

Users of one specific app

Adds features to that one app

MCP server

Any MCP-compatible AI app

Describes a product's actions and data so a model can use them

AI agent

End users

Plans and runs steps, often by calling MCP tools

An API is written for a developer who reads docs; an MCP server is read by a model at runtime, so clear tool names become part of your UX. Our guide to agentic UX covers what happens when an agent chains those tools.

What does MCP look like for designers and founders?

For designers, MCP lets a coding agent read a Figma frame's layers, variables and components instead of guessing from an image. For founders, it lets an assistant pull from your CMS, docs or database.

Hypothetical example: an agent reading a Figma file and a CMS

For example, suppose a founder wants a new pricing section. Their coding editor has two MCP servers connected: Figma's and their CMS's.

They paste a link to the pricing frame. The agent calls a Figma tool for the frame's structure and variables, then a CMS tool for current plan names and prices, and writes the section with existing components. Before any CMS tool that would publish, the editor asks for approval. The founder reviews the diff, fixes mobile spacing and ships it.

Our guides to the Figma MCP server and Figma to code with AI cover where a developer still steps in.

What are common misconceptions about MCP?

The most common mistake is treating MCP as a feature users see. It's plumbing. Users see approvals, connected accounts and tool activity, and those need design.

  • "MCP makes AI accurate." It gives the model better context, but the model can still misread data or call the wrong tool.
  • "An MCP server is secure by default." The server only has the access you grant. Scopes, consent and revoking access are your job to design.
  • "Every client supports everything." Support for MCP features varies by client and changes often, so check each client's docs.

Frequently asked questions

Who created the Model Context Protocol?
Anthropic introduced the Model Context Protocol as an open standard, and many AI apps and products beyond Anthropic's now support it. The specification, SDKs and documentation are public at modelcontextprotocol.io. Because it's open, any company can build a server for its product or a client for its AI app without a license fee.
Do I need to code to use an MCP server?
Usually not to use one. Many AI apps let you add a remote MCP server by pasting a URL or picking it from a list, then signing in. Building a server is developer work, because it means wrapping your product's API and writing clear tool descriptions.
Is MCP safe to connect to my company's tools?
MCP is as safe as the access you grant and the server you trust. Connect only servers from vendors you trust, prefer read-only access where offered, and review any tool call that writes or deletes data. Admins should check which servers employees connect and revoke access that's no longer needed.
What's the difference between MCP and a custom GPT or AI plugin?
A custom GPT or plugin is built for one AI app and its ecosystem. An MCP server follows an open standard, so the same server can work across many MCP-compatible apps, from chat assistants to coding editors. In practice, that means a product team builds and maintains one integration instead of one per AI platform, and users can bring it to the tools they already use.

· CEO & Design Director

Copywriter, designer and developer, and founder of Designify Studio. Over five years, 60+ projects across 14+ industries, for startups that have raised $300M+.

Want us to do this for you?

We take craft seriously over at Designify Studio. We do deep research and do what we do best - pay attention to the smallest details and make sure we speak to the right audience.

Schedule Call