Securing AI agents: How AWS and Cisco AI Defense scale MCP and A2A deployments

2026-05-13 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cybersecurity & Data Privacy, Robotics & Autonomous Systems · Depth: Intermediate, medium

Summary

AWS and Cisco AI Defense have partnered to address critical security gaps in enterprise AI agent deployments, which have rapidly scaled since the introduction of the Model Context Protocol (MCP) in November 2024 and the Agent-to-Agent (A2A) Protocol in April 2025. The collaboration provides automated security scanning and unified governance for MCP servers, A2A agents, and Agent Skills. This initiative tackles challenges such as tool sprawl, lack of visibility into deployed AI components, unscalable manual security reviews, and the absence of audit trails required for compliance frameworks like SOX and GDPR. The solution integrates the AWS-backed open-source AI Registry for centralized registration and discovery with Cisco AI Defense's comprehensive scanning capabilities, ensuring that all AI assets are vetted for vulnerabilities and malicious patterns before deployment.

Key takeaway

For CTOs and VPs of Engineering scaling AI agent deployments, you should prioritize implementing automated security scanning and a unified governance framework. Leveraging solutions like the AWS AI Registry and Cisco AI Defense integration can provide essential visibility, streamline compliance, and prevent security bottlenecks that hinder rapid AI adoption. Ensure your teams integrate these scanning capabilities into CI/CD pipelines to proactively identify and mitigate risks from unvetted MCP servers, A2A agents, and Agent Skills.

Key insights

Automated security scanning and unified governance are crucial for scaling enterprise AI agent deployments securely.

Principles

• Centralized registration improves AI asset visibility.
• Automated scanning prevents supply chain vulnerabilities.
• Audit trails are essential for regulatory compliance.

Method

The AI Registry centralizes MCP servers, A2A agents, and Skills. Cisco AI Defense scanners (YARA, LLM, Proprietary) automatically analyze these assets for threats, disabling vulnerable components and generating detailed security reports for administrator review.

In practice

• Integrate security scanning into CI/CD workflows.
• Configure periodic scans of the entire AI Registry.
• Forward issue data to SIEM systems like Splunk.

Topics

• AI Agent Security
• Model Context Protocol
• Agent-to-Agent (A2A) Protocol
• Cisco AI Defense
• AWS AI Registry

Code references

• agentic-community/mcp-gateway-registry
• awslabs/agentcore-samples
• cisco-ai-defense/mcp-scanner
• cisco-ai-defense/a2a-scanner
• cisco-ai-defense/skill-scanner

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Security Engineer, MLOps Engineer, AI Architect

Related on AIssential

• DAY 2 Livestream - 5-Days of AI Agents: Intensive Vibe Coding Course With Google — Open protocols like MCP, A2A, and A2UI standardize agent interoperability, reducing complexity and enabling advanced AI applications.
• AI, A2A, and the Governance Gap — Agent protocols like A2A and ACP create a governance gap by enabling autonomous actions faster than organizations can establish control.
• AI Agents Will Accelerate DevOps Maturity, and it’s Vital Your Security Keeps Pace — AI agents accelerate DevOps maturity through automation but demand robust security measures to mitigate inherent risks.
• AAIF's MCP Dev Summit: Gateways, gRPC, and Observability Signal Protocol Hardening — MCP is maturing into a critical enterprise integration protocol for agentic AI, driven by stateless transports and gateway architectures.
• AI agents are running hospital records and factory inspections. Enterprise IAM was never built for them. — Identity governance, not model capability, is the primary barrier preventing agentic AI from moving from pilot to production.
• AWS previews a cloud-agnostic registry for managing agentic fleets at scale — AWS Agent Registry centralizes AI agent discovery and governance to prevent "agentic sprawl" and enhance reuse.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.