Guardrail sidecar proxy between AI agents and their MCP/REST/CLI tools. Policy engine, human approval gates, time-limited grants, rate limiting, and OTEL tracing. One Go binary, one YAML config, fail-closed by default.
A defensive gateway and firewall for AI agents using MCP servers, scanning tool calls, responses, and manifests for prompt injection, secrets, dangerous commands, and drift before allowing execution.
Security, cost, and health governance proxy for MCP infrastructure. Enforces YAML-configurable security policies (blocklists, rate limits, token budgets), tracks real token costs via tiktoken, monitors server health with live JSON-RPC probes. Features OAuth 2.1/OIDC with RBAC, web dashboard, payload normalization, semantic shell AST analysis, mTLS, and a formal STRIDE threat model.