Whenever you first hear about MCP — Mannequin Context Protocol, it appears like one thing constructed for hardcore AI researchers. However right here’s the fact: Community engineers and automation engineers are going to be a few of the greatest customers of it.
In case you’re questioning why: MCP is the way you make Massive Language Fashions (LLMs) perceive your community, your topology, your requirements, your world.
With out it? You’re simply getting generic ChatGPT solutions.
With it? You’re creating Agentic AI that may configure, troubleshoot, and design networks with you.
I’ve been speaking to you — You! …Sure, you! — about community automation and adopting automation in your community engineering for years now. All in all, it’s time so as to add one other brick in *your* wall (of tech instruments). On this AI Break, we’ll discover an instance that demonstrates the worth of utilizing MCP to grasp automation in right this moment’s AI world.
Okay, so what’s MCP?
At its coronary heart, Mannequin Context Protocol is about injecting structured data into an LLM at runtime — mechanically and programmatically.
As an alternative of manually pasting community diagrams or config templates right into a chat window, MCP lets your instruments inform the mannequin:
- What gadgets are on the community
- What requirements you utilize
- What applied sciences you like (OSPF over EIGRP, EVPN over VXLAN, no matter)
- What change management processes exist
All that context flows into the mannequin, making its responses smarter, extra aligned, and extra helpful to your surroundings.
Let’s begin with a fundamental, real-world instance
Let’s say you’re constructing an LLM-based Community Assistant that helps generate configs. You don’t need it suggesting RIP when your whole community runs OSPF and BGP.
With MCP, earlier than you even ask the mannequin for a config, you present AI with the next context:
Look acquainted? Yup, it’s a JSON.
{
"network_standards": {
"routing_protocols": ["OSPF", "BGP"],
"preferred_encapsulation": "VXLAN",
"security_policies": {
"ssh_required": true,
"telnet_disabled": true
}
},
"topology": {
"core_devices": ["core-sw1", "core-sw2"],
"edge_devices": ["edge-fw1", "edge-fw2"],
"site_layout": "hub and spoke"
}
}
Your assistant mechanically sends this context to the LLM utilizing MCP, and then asks, “Generate a config to onboard a brand new web site.”
The mannequin now solutions in a means that matches your surroundings— not some random textbook response.
So, what expertise do it’s essential to use MCP?
Truthfully, a variety of you have already got most of what’s wanted:
- API Fundamentals. You’ll be sending structured context (often JSON) over API calls — identical to RESTCONF, NETCONF, Catalyst Heart, Or Meraki APIs.
- Understanding your community metadata. It’s essential know what issues: routing, VLANs, safety, system varieties, and how one can symbolize that as structured knowledge.
- Python scripting. You’ll in all probability use Python to gather this information dynamically (like through Nornir, Netmiko, or native APIs) after which bundle it into MCP calls.
- LLM fundamentals. It’s essential perceive how prompts and context home windows work, and the way larger context equals smarter outputs.
The underside line
MCP isn’t some “perhaps later” factor for networkers.
It’s turning into the bridge between your real-world community data and AI’s capability that can assist you sooner, higher, and extra precisely.
Engineers who know how one can feed actual context into LLMs will dominate community design, troubleshooting, safety auditing, and even full-stack automation.
Begin now
- Map your community requirements.
- Package deal them as JSON.
- Play with sending that context into small AI workflows.
The very best AI Brokers are constructed by engineers who know their community—and know how one can train it to their AI. Subsequent, let’s get hands-on with MCP!
Strive it
For a completely working code and directions to get began, take a look at my undertaking on GitHub.
Create a actual Mannequin Context Protocol (MCP) server designed for community engineers.
This MCP app does the next:
- Serve your community requirements (routing protocols, safety insurance policies, and so forth.)
- Reply with system well being
- Hook up with Claude Desktop, making your AI assistant conscious of your actual community surroundings
And it’s so simple as:
- Import the MCP Python SDK
from mcp.server.fastmcp import FastMCP
- Initialize the FastMCP server with a singular title
mcp = FastMCP("network-assistant")
- Outline instruments.
Instruments are a robust primitive within the Mannequin Context Protocol (MCP). They let your server expose actual actions—so the mannequin can question programs, run logic, or kick off workflows. In our use case, we have to outline ‘network-standards’ & ‘system standing’ features:@mcp.device() async def get_network_standards() -> dict[str, Any]: """Returns customary routing protocols, encapsulation, and safety insurance policies.""" return NETWORK_STANDARDS
- Run the server, and you might be set!
if __name__ == "__main__": mcp.run(transport="stdio")
And if we have a look at it, that is what the LLM is aware of about your community earlier than you contextualized it:
And that is after connecting the LLM to our Community:
The place community automation and AI really collide
You’re not scripting for the sake of scripting. And also you don’t simply use AI for the sake of buzzwords. When you may mix stay community state with LLM intelligence, you’re constructing programs that suppose, adapt, and help with you—not simply for you.
Begin easy. Construct one stream.
Make your AI agent really know your community. As a result of the longer term belongs to engineers who don’t simply automate—they contextualize.
Welcome to the brand new frontier of Agentic AI!
Get began with AI
Studying Paths, programs, free tutorials, and extra. Unlock the way forward for know-how with synthetic intelligence coaching in Cisco U. Discover AI studying and begin constructing your expertise right this moment.
Join Cisco U. | Be a part of the Cisco Studying Community right this moment without spending a dime.
Observe Cisco Studying & Certifications
X | Threads | Fb | LinkedIn | Instagram | YouTube
Use #CiscoU and #CiscoCert to hitch the dialog.
Adaptability: The Should-Have Talent for Community Engineers within the AI Period
MCP for DevOps, NetOps, and SecOps: Actual-World Use Circumstances and Future Insights
Share:
