[Webinar] Securing Agentic AI: From MCPs and Tool Access to Shadow API Key Sprawl

According to The Hacker News, a forthcoming webinar on securing agentic AI examines how MCPs—Machine Control Protocols—sit behind agentic AI workflows, governing what an AI agent can run, which tools it can call, which APIs it can access and what infrastructure it can touch. The event notes that if an MCP control plane is compromised or misconfigured, the agent can act with authority and automate actions at scale.

It cites CVE-2025-6514 as an example where a trusted OAuth proxy used by more than 500,000 developers became a remote code execution path, illustrating how an agent that can execute commands can also execute attacks. The session aims to show where shadow API keys come from, how permissions can quietly sprawl, and why traditional identity and access models break down when agents act on your behalf. The article, dated 13 January 2026, emphasises practical controls to secure agentic AI without slowing development.