As the developer community gathers in Seoul, the tension between architectural design and real-world vulnerability has moved to the center of the AI agent infrastructure debate. More than 21,000 internet-facing MCP server instances are currently exposed, with nearly 92% of audited production servers lacking basic OAuth authentication. This data, surfacing alongside a growing catalog of critical CVEs and the formalization of the OWASP MCP Top 10, has transformed the Model Context Protocol (MCP) Dev Summit in Seoul this August 13–14, 2026, from a routine industry check-in into a high-stakes confrontation. The OX Security ‘Mother of All AI Supply Chains’ report, published in April 2026, identified a systemic architectural vulnerability in the MCP STDIO transport, with 150 million downstream package downloads potentially affected, over 7,000 publicly accessible MCP servers, and up to 200,000 vulnerable instances identified. Anthropic has maintained that the STDIO behavior is ‘by design,’ asserting that the execution model serves as a ‘secure default’ and that input sanitization remains the responsibility of the developer. Research published in arXiv 2608.00150 ‘Exposed by Design’ in July 2026 detected over 21,000 internet-facing MCP server instances; of the 640 production servers audited, 91.8% lacked OAuth, and 687 instances were found to have unrestricted shell tool access. These figures are compounded by