Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by vitas • Uncategorized
An MCP server that validates destructive infrastructure commands against explicit policies to prevent unsafe operations.
Safely execute destructive infrastructure commands with policy validation.
Prevent catastrophic misconfigurations in Kubernetes, Terraform, ArgoCD, and cloud resources.
An auditable, tamper-evident log of all infrastructure operation decisions.
Evidra-Lock acts as a kill-switch layer between AI agents and infrastructure tools like kubectl, terraform, and argocd, blocking destructive operations unless they are explicitly allowed by policy. It uses deterministic OPA policy evaluation to deny unsafe, incomplete, or ambiguous commands, recording every decision in a tamper-evident hash-chained evidence log. This ensures safer AI-driven infrastructure automation and CI pipeline execution without relying on natural language processing or runtime network calls.