Model Context Protocol (MCP)

Weekly roundup covering zero trust controls for agentic AI, CISA Secure Boot guidance, and AI infrastructure governance announcements.

Weekly roundup covering enterprise AI guardrails and agent security, sovereign AI platforms, security advisories, and AI infrastructure market signals.

Digital Realty made ServiceFabric MCP available as a programmable control layer for Private AI across its global interconnection platform.

Nokia added an agentic AI framework to NSP for IP networks, grounding agents in real-time context and enabling guided troubleshooting within policies.

Netskope says zero trust models for human access don’t cover AI agents using MCP and app-to-LLM traffic, and describes related visibility controls.

Cequence Security said AI security focus should shift from authentication to controlling AI agent behavior using its AI Gateway approach.

The article describes Aviz Networks’ NCP Agent SDK, an on-premises, vendor-neutral platform for building AI agents that query network data, correlate context, and perform governed actions.

Infoblox IQ combines agentic actions, a natural language assistant, and an MCP Server to triage alerts and support remediation.

Itential previews Cisco Live US and AutoCon 5 with FlowAI live demos and sessions on RAG, MCP, and agent operations.

Cycode released ADLC Security generally available, adding AI visibility, governance, guardrails, and risk detection for agentic development.

The blog describes how AI pilots get stuck in security reviews and outlines Netskope tools for risk scoring, semantic DLP, agent controls, and lower latency.

JumpCloud introduced Agentic IAM to govern human and non-human agent identities through discovery, AI gateway controls, device trust, and HITL checkpoints.