Integrate MCP Servers Into Your Agents
In this session, you’ll first discover what the Model Context Protocol (MCP) is—an open standard that provides a universal interface for AI applications to connect with external data sources and tools, akin to a “USB-C port for AI,” simplifying custom integrations and ensuring consistent two-way communication between LLMs and services. You’ll then build a lean MCP server in Python using the ultrafast uv tool to manage dependencies and run scripts in one unified workflow. Finally, you’ll harness OpenAI agents’ function-calling features to invoke your MCP endpoints automatically—demonstrating how AI-driven agents can orchestrate dynamic, intelligent workflows.
In summary, we'll walk through:
- What is MCP, and why it matters
- Writing a small MCP server in Python + uv
- Using OpenAI agents to call said MCP server
Presented by DeepStation, in partnership with Miami Dade College for community outreach and engagement. DeepStation accelerates AI education and innovation through the power of community, empowering engineers, business professionals, and enthusiasts to thrive in the AI wave. The global community teaches AI, connects local talent with industry, and facilitates economic development through expert-led presentations, hands-on workshops, and regional industry summits. The community has established chapters in Miami, Brazil, and is expanding to new regions worldwide.
Speakers
