Skip to main content

AgentSuite Platform Overview

AgentSuite-Guard is an end-to-end runtime protection suite for agentic systems. The Virtue Gateway sits between your AI agents and your MCP servers and APIs, enforcing security policies at every layer of agent execution.

Architecture​

AgentSuite-Guard Architecture

The gateway provides the following protection layers:

  • Prompt Guard — Detect and block prompt injection attacks before they reach the agent
  • MCP Guard — Scan MCP tool descriptions and source code for vulnerabilities and tool poisoning
  • AgentGuard — Monitor and block unsafe agent actions at runtime against configurable policies (EU AI Act, GDPR, OWASP LLM Top 10, and custom policies)
  • Net Guard — Network-level traffic protection
  • Access Control — Per-user and per tool and data source permissions
  • Shadow AI — Detect and manage unsanctioned AI usage across your organization
  • Observability — Full trajectory logging of every agent session with inline guardrail decisions

Deployment​

We provide SaaS and on-premise deployment options for the Agent Gateway. For SaaS deployment, a hosted dashboard endpoint is provided and all functionality is available immediately. For on-premise deployment, the platform can be deployed using Docker containers with your own database.

Start Here​

MCP & Gateway Web UI

Set up your gateway, connect MCP servers, configure access control, and link your AI clients via connectors.

SDK & ADK Integration

SDK integration guides for Google ADK, OpenAI Agents SDK, LangChain, Claude, Strands, and Microsoft 365 Agents — with full gateway security coverage.