Back to Browse
Free
Server data from the Official MCP Registry
Fail-closed policy guardrails for AI agents running kubectl, terraform, helm, and argocd.
About
Fail-closed policy guardrails for AI agents running kubectl, terraform, helm, and argocd.
Remote endpoints: streamable-http: https://evidra.samebits.com/mcp
What You'll Need
Set these up before or after installing:
Enable deny-loop prevention cache for agent/CI actors
Environment variable: EVIDRA_DENY_CACHE
Environment label for policy evaluation (e.g. production, staging)
Environment variable: EVIDRA_ENVIRONMENT
How to Install & Connect
Available as Local & Remote
This plugin can run on your machine or connect to a hosted endpoint. during install.
Security Report
6.0
Moderate6.0Moderate RiskThe Evidra MCP server demonstrates excellent security practices with proper authentication design, clean code structure, and permissions that appropriately match its purpose as a security-focused infrastructure validation tool. Only minor code quality issues were identified that do not significantly impact the overall security posture. Supply chain analysis found 6 known vulnerabilities in dependencies (1 critical, 0 high severity).
Scanned 4 files · 8 findings
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
Reviews
No reviews yet
Be the first to review this server!