Gartner projects the average Fortune 500 will run over 150,000 AI agents by 2028, up from fewer than 15 in 2025, and only 13% of organizations believe they have adequate governance. Without a shared coordination layer, you are not running a multi-agent system — you are running a distributed system with no contract between its components.

Tun Shwe and Jeremy Frenay at Lenses argue that MCP servers fail in production not because of missing auth, but because teams expose agent-facing tools like human APIs. Security starts at interface design—fewer tools, constrained inputs, minimal data exposure—before a single line of OAuth code.

Simon Willison argues that coding agents become trustworthy when you stop reviewing their code line-by-line and start demanding proof: red-green TDD, runtime smoke tests, conformance suites, and sandboxed execution. The shift from human review to automated verification is what makes agent autonomy viable.

Notes from KubeCon EU 2026 in Amsterdam and Agentics Day: MCP is converging as the enterprise protocol for agent-to-system connectivity, agent gateways are emerging as the coordination layer for AI traffic, and OpenTelemetry is becoming the shared observability standard. The bar everyone kept coming back to: the effort to supervise agents must be lower than the work they take off the table.

Amplifon built a centralized registry system for MCP servers and A2A agents across 26 countries and 10,000+ stores. The architecture—registries, metadata, blueprints, CI/CD-driven discovery—offers a concrete answer to the enterprise agent sprawl problem most organizations haven't started solving.