What you'll learn

The Model Context Protocol (MCP) is quickly becoming the standard way AI agents connect to tools, data sources, and one another — and with that power comes a new class of vulnerabilities that traditional application security controls don't fully address. In this course, OWASP MCP Top 10: Securing the Model Context Protocol, you will learn how to identify, exploit in a controlled lab setting, and remediate the ten most critical MCP security risks published by OWASP. You will explore how credentials and privileges leak or expand unexpectedly, how malicious tool descriptions and contextual payloads hijack agent behavior, how supply chain and command injection flaws let attackers execute code through agent workflows, and how insufficient authentication, missing audit trails, shadow servers, and context over-sharing quietly erode trust in production MCP deployments. By the end of this course, you will be able to assess an MCP deployment against the OWASP MCP Top 10, prioritize remediation, and build the governance practices needed to run MCP safely at scale.