The Center for Internet Security, Inc. (CIS), Astrix Security, and Cequence Security released three new AI security companion guides on April 22, 2026, designed to help enterprises secure rapidly evolving artificial intelligence environments. Co-authored by experts across all three organizations, the guides extend the CIS Critical Security Controls into AI systems where large language models, autonomous agents, and Model Context Protocol integrations introduce new risks.

Each guide focuses on a distinct layer of the artificial intelligence ecosystem. The AI LLM Companion Guide provides guidance for securing large language models, including risks related to prompts, context handling, and exposure of sensitive information. The AI Agent Companion Guide outlines controls for managing autonomous and semi-autonomous agents, focusing on safe tool execution, governed autonomy, and appropriate access to enterprise systems. The MCP Companion Guide details protections for Model Context Protocol environments, emphasizing secure tool access, management of Non-Human Identities, and auditable interactions across the protocol layer.

As artificial intelligence becomes deeply embedded in production workflows, security teams face risks that traditional controls were never built to address. These include data leakage, unbounded agent autonomy, credential misuse, and unsafe or inappropriate execution of tools. The new guides offer practical, prioritized guidance that reflects how AI is actually deployed in modern enterprises.

“These guides reflect a shared effort to bring clarity to an area where organizations are seeking direction. By combining our collective expertise, we translated the CIS Controls into concrete steps that help teams secure AI systems across the model, agent, and protocol layers.”

Curtis Dukes, Executive Vice President and General Manager of Security Best Practices at CIS

How the Guides Support Organizations

The three guides give security and IT teams a unified way to apply the CIS Controls to AI systems that behave and evolve differently from traditional software. By extending the Controls into environments powered by large language models, autonomous agents, and MCP-based integrations, the guidance helps organizations understand where risks emerge and how to address them with guidance that reflects real-world deployment patterns.

  • Adapt the CIS Controls to AI-driven architectures, helping teams secure large language models, agentic systems, and MCP interfaces without adopting a new framework
  • Provide clear, prioritized recommendations that support responsible AI adoption across development, deployment, and operational phases
  • Blend the strengths of all three organizations by combining standards leadership with deep expertise in agentic AI and API-centric security
  • Cover the full AI security stack, from model inputs and context handling to agent reasoning, tool execution, and protocol-level access

Expertise From Three Organizations

Astrix contributed deep expertise in securing AI agents, MCP servers, and Non-Human Identities, including API keys, service accounts, and OAuth tokens that connect AI systems to enterprise resources. Jonathan Sander, Field CTO of Astrix Security, stated that “AI agents introduce a new operational surface that organizations must understand before they scale. Collaborating with CIS and Cequence allowed us to build guidance that addresses identity, authorization, and execution risks in a way that’s both actionable and aligned with how enterprises work today.”

Cequence brought extensive experience in securing enterprise applications, data, and APIs, shaping guidance around visibility, governance, and control over what AI systems can access and execute. Shreyans Mehta, CTO and Co-Founder of Cequence Security, said that “as AI systems interact more directly with applications and APIs, the security implications become increasingly critical. This partnership enabled us to create guidelines that codify what we’ve learned about deploying agentic AI at the world’s largest enterprises without sacrificing security, governance, or scale.”

Upcoming Webinar and Resources

CIS, Astrix, and Cequence will host a webinar on May 13 at 1:00 p.m. ET titled “From Prompts to Protocols: The Security Blueprint for Enterprise AI.” The teams will highlight key insights and offer guidance for security teams, developers, and AI practitioners. Additional information about the partnership and the guides is available through CIS’s official channels.