Guard Starter is the human gate inside SentinelAgent Guard: allow / ask / deny for MCP and agent tool calls across Cursor, Claude Code, Cline, and other MCP hosts. Deterministic policies, no model in the approval path. Deny returns a readable refusal, not a hang; decisions land in an audit log. Starter free: local allow / ask / deny, short audit, 1 seat. Starter Pro: $19/mo, cloud sync and longer audit. Guard Pro $49/mo is a soft upsell, not the PH headline price. Same Guard brand. Same site.

Guard sits in front of your MCP server and runs 22 deterministic checks across five layers on every call. It blocks tool poisoning, rug pulls (CVE-2025-54136), and hidden Unicode payloads in tool descriptions before they land. No AI model does the checking — same verdict every time, no token bill. Point your agent at Guard instead of building this yourself. Three ways to run the same engine: hosted gateway, embedded SDK, or sidecar CLI for Cursor / Claude Code / Copilot stdio servers.