Kubernetes-native governance for MCP infrastructure: it watches agentgateway and kagent resources, scores security posture per MCP server, and explains the risks using Gemini or Ollama.
The core move is turning security posture — normally a vague word — into a score per MCP server, because once something has a number it can be ranked and argued about. Watching agentgateway and kagent means the work sits directly on the host's own components rather than beside them. Offering Ollama alongside Gemini for the risk explanations suggests the team pictured organisations that cannot send infrastructure detail to an outside model, which reads as production thinking.
See all winners of Hackathon for MCP & AI Agents (Solo.io) →
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).