Zayo, the leading digital network infrastructure provider, launched Agentic Networking for DynamicLink, advancing NaaS from software-defined network control to a new model that enables enterprise AI agents to work directly with the network for the first time.

Zayo introduced a new approach to software-defined networking with DynamicLink in September 2025. Now, as DynamicLink reaches its first year in production, Zayo is introducing the industry’s first production MCP server built for networking, progressing DynamicLink from self-service network control to Agentic Networking. This gives approved AI agents a governed way to understand network conditions, access network tools, and take authorized action.

“Together, Zayo’s network infrastructure, DynamicLink platform, networking skill, and MCP server create a capability that has not previously existed,” said Chris Ranalli, Chief Revenue Officer for Enterprise at Zayo. “This combination creates a way for approved AI agents to understand what is happening across the network, access network tools, and execute authorized actions. Instead of simply asking AI questions about the network, enterprises can put AI to work on it.”

What This Capability Enables

Agentic Networking brings network context and authorized network actions into the AI workflows enterprises are already building. Agents can use DynamicLink’s product and network knowledge resources to understand network conditions, while retrieval-augmented generation (RAG) helps ground interactions in the DynamicLink knowledge base. Organizations define the information, tools, and actions available to agents, with automation, governance, and human oversight remaining in place.

Potential workflows include:

• Establishing cloud-to-cloud connectivity: Coordinate the steps required to connect approved cloud environments without engineers manually moving between multiple systems.
• Investigating network performance: Gather and correlate context across network, cloud, and application environments to help identify the source of an issue and recommend next steps.
• Coordinating multi-cloud connectivity: Help teams understand and manage connectivity requirements as workloads move across cloud environments.
• Responding to unusual network activity: Surface relevant network context, identify potential issues, and recommend actions for an engineer to review.
• Executing approved network changes: Invoke authorized DynamicLink tools to carry out network or security actions within enterprise-defined controls.
• Extending networking into enterprise AI workflows: Enable organizations to build network operations into approved AI agents and workflows beyond the DynamicLink portal.

For network teams, this means less time moving between systems and coordinating routine tasks and more time focused on higher-value decisions. This efficiency is especially valuable for industries like retail, financial services, healthcare, and media and entertainment organizations managing increasingly data-intensive environments.

Why This Matters

The first generation of NaaS gave enterprises software-based visibility and control over network infrastructure. Agentic Networking changes how that control is consumed by making network capabilities accessible within the AI systems enterprises are already using to coordinate work across applications, clouds, and other systems.

“Enterprise AI will increasingly be measured by what it can responsibly accomplish across the systems that run the business,” said Max Clauson, SVP of Network Connectivity at Zayo. “The future of networking is not another portal. It's making network capabilities available within the AI systems enterprises use to run their business. Agentic Networking gives organizations a path toward that future, where AI can take on more operational work while people maintain authority over the infrastructure underneath it.”