Skip to main content

Radar > Topics > Zero to Agent in 30 Minutes

Zero to Agent in 30 Minutes: Build Your First Agent with MCP

Turn existing APIs into tools an AI assistant can use

Michelle Smith

By Michelle Smith October 5, 2026 • 3 minute read

Developers already have useful capabilities exposed through REST APIs. The Model Context Protocol (MCP) lets developers make those capabilities available to AI clients without rebuilding the underlying application.

In this episode of Zero to Agent in 30 Minutes, Bruce Hopkins, an AI developer, author, and longtime software educator, shows how to do that with an MCP server. His demo wraps an existing stock-data API in an MCP server so an MCP client can call it.

From REST API to MCP, step-by-step

  1. Start with an existing API. Identify the operations and data you want an AI client to access. The demo uses the Twelve Data API to retrieve current and historical stock prices.
  2. Create an MCP server. Use an MCP SDK to create the layer between the AI client and your existing application logic. In Bruce’s Python example, FastMCP handles the MCP interface while the stock-data functions remain separate.
  3. Expose capabilities as tools and resources. Register the operations the client should be able to discover and call. The stock-price data is exposed through MCP resources and tools that reuse the same underlying functions.
  4. Describe how the client should use them. Define clear names, inputs, descriptions, and prompts so the client understands what each capability does and what information it requires. Bruce’s example includes prompts for current prices, historical prices, and expected symbol and date formats.
  5. Connect the server to an MCP client. Run the server over a supported transport so the client can discover and call its tools and resources. 

You don’t need to replace the systems that already handle your application logic to help them work with agents. You can add an MCP interface around existing capabilities to give an AI client a standard way to discover and use them. Be sure to check out Bruce’s GitHub repo for working code you can adapt for your own APIs.

Coming next week

Next week, AI engineer Sajal Sharma returns to Zero to Agent in 30 Minutes to build a personal assistant on OpenClaw. He’ll show how an agent can keep tasks and notes in Markdown, run proactive automations, and deliver scheduled updates such as a regular morning briefing without waiting for a new prompt.

Follow along with Zero to Agent in 30 Minutes on Radar, or watch the latest episode on YouTube, Spotify, Apple, or wherever you get your podcasts. If you’re an O’Reilly member, you can watch live. Save your seat.

Post topics: Zero to Agent in 30 Minutes