Hey there, everybody, and welcome to the most recent installment of “Hank shares his AI journey.” 🙂 Synthetic Intelligence (AI) continues to be all the trend, and getting back from Cisco Stay in San Diego, I used to be excited to dive into the world of agentic AI.
With bulletins like Cisco’s personal agentic AI resolution, AI Canvas, in addition to discussions with companions and different engineers about this subsequent section of AI prospects, my curiosity was piqued: What does this all imply for us community engineers? Furthermore, how can we begin to experiment and find out about agentic AI?
I started my exploration of the subject of agentic AI, studying and watching a variety of content material to achieve a deeper understanding of the topic. I received’t delve into an in depth definition on this weblog, however listed below are the fundamentals of how I give it some thought:
Agentic AI is a imaginative and prescient for a world the place AI doesn’t simply reply questions we ask, but it surely begins to work extra independently. Pushed by the objectives we set, and using entry to instruments and programs we offer, an agentic AI resolution can monitor the present state of the community and take actions to make sure our community operates precisely as supposed.
Sounds fairly darn futuristic, proper? Let’s dive into the technical features of the way it works—roll up your sleeves, get into the lab, and let’s be taught some new issues.
What are AI “instruments?”
The very first thing I wished to discover and higher perceive was the idea of “instruments” inside this agentic framework. As it’s possible you’ll recall, the LLM (giant language mannequin) that powers AI programs is basically an algorithm skilled on huge quantities of information. An LLM can “perceive” your questions and directions. On its personal, nonetheless, the LLM is restricted to the info it was skilled on. It might’t even search the online for present film showtimes with out some “instrument” permitting it to carry out an internet search.
From the very early days of the GenAI buzz, builders have been constructing and including “instruments” into AI purposes. Initially, the creation of those instruments was advert hoc and various relying on the developer, LLM, programming language, and the instrument’s purpose. However not too long ago, a brand new framework for constructing AI instruments has gotten loads of pleasure and is beginning to change into a brand new “commonplace” for instrument improvement.
This framework is called the Mannequin Context Protocol (MCP). Initially developed by Anthropic, the corporate behind Claude, any developer to make use of MCP to construct instruments, referred to as “MCP Servers,” and any AI platform can act as an “MCP Consumer” to make use of these instruments. It’s important to do not forget that we’re nonetheless within the very early days of AI and AgenticAI; nonetheless, presently, MCP seems to be the method for instrument constructing. So I figured I’d dig in and determine how MCP works by constructing my very own very primary NetAI Agent.
I’m removed from the primary networking engineer to wish to dive into this house, so I began by studying a few very useful weblog posts by my buddy Kareem Iskander, Head of Technical Advocacy in Study with Cisco.
These gave me a jumpstart on the important thing matters, and Kareem was useful sufficient to supply some instance code for creating an MCP server. I used to be able to discover extra alone.
Creating a neighborhood NetAI playground lab
There isn’t a scarcity of AI instruments and platforms as we speak. There may be ChatGPT, Claude, Mistral, Gemini, and so many extra. Certainly, I make the most of lots of them commonly for numerous AI duties. Nonetheless, for experimenting with agentic AI and AI instruments, I wished one thing that was 100% native and didn’t depend on a cloud-connected service.
A major purpose for this want was that I wished to make sure all of my AI interactions remained completely on my laptop and inside my community. I knew I might be experimenting in a completely new space of improvement. I used to be additionally going to ship knowledge about “my community” to the LLM for processing. And whereas I’ll be utilizing non-production lab programs for all of the testing, I nonetheless didn’t like the concept of leveraging cloud-based AI programs. I might really feel freer to be taught and make errors if I knew the danger was low. Sure, low… Nothing is totally risk-free.
Fortunately, this wasn’t the primary time I thought-about native LLM work, and I had a few attainable choices able to go. The primary is Ollama, a robust open-source engine for working LLMs domestically, or at the least by yourself server. The second is LMStudio, and whereas not itself open supply, it has an open supply basis, and it’s free to make use of for each private and “at work” experimentation with AI fashions. Once I learn a current weblog by LMStudio about MCP help now being included, I made a decision to offer it a attempt for my experimentation.
LMStudio is a consumer for working LLMs, but it surely isn’t an LLM itself. It offers entry to numerous LLMs obtainable for obtain and working. With so many LLM choices obtainable, it may be overwhelming once you get began. The important thing issues for this weblog publish and demonstration are that you simply want a mannequin that has been skilled for “instrument use.” Not all fashions are. And moreover, not all “tool-using” fashions truly work with instruments. For this demonstration, I’m utilizing the google/gemma-2-9b mannequin. It’s an “open mannequin” constructed utilizing the identical analysis and tooling behind Gemini.
The following factor I wanted for my experimentation was an preliminary thought for a instrument to construct. After some thought, I made a decision a great “hey world” for my new NetAI challenge could be a method for AI to ship and course of “present instructions” from a community system. I selected pyATS to be my NetDevOps library of selection for this challenge. Along with being a library that I’m very conversant in, it has the advantage of automated output processing into JSON by the library of parsers included in pyATS. I might additionally, inside simply a few minutes, generate a primary Python operate to ship a present command to a community system and return the output as a place to begin.
Right here’s that code:
def send_show_command(
command: str,
device_name: str,
username: str,
password: str,
ip_address: str,
ssh_port: int = 22,
network_os: Non-obligatory[str] = "ios",
) -> Non-obligatory[Dict[str, Any]]:
# Construction a dictionary for the system configuration that may be loaded by PyATS
device_dict = {
"units": {
device_name: {
"os": network_os,
"credentials": {
"default": {"username": username, "password": password}
},
"connections": {
"ssh": {"protocol": "ssh", "ip": ip_address, "port": ssh_port}
},
}
}
}
testbed = load(device_dict)
system = testbed.units[device_name]
system.join()
output = system.parse(command)
system.disconnect()
return output
Between Kareem’s weblog posts and the getting-started information for FastMCP 2.0, I realized it was frighteningly simple to transform my operate into an MCP Server/Instrument. I simply wanted so as to add 5 traces of code.
from fastmcp import FastMCP
mcp = FastMCP("NetAI Hiya World")
@mcp.instrument()
def send_show_command()
.
.
if __name__ == "__main__":
mcp.run()
Effectively.. it was ALMOST that simple. I did must make just a few changes to the above fundamentals to get it to run efficiently. You may see the full working copy of the code in my newly created NetAI-Studying challenge on GitHub.
As for these few changes, the modifications I made have been:
- A pleasant, detailed docstring for the operate behind the instrument. MCP purchasers use the main points from the docstring to know how and why to make use of the instrument.
- After some experimentation, I opted to make use of “http” transport for the MCP server relatively than the default and extra frequent “STDIO.” The explanation I went this manner was to arrange for the following section of my experimentation, when my pyATS MCP server would seemingly run inside the community lab atmosphere itself, relatively than on my laptop computer. STDIO requires the MCP Consumer and Server to run on the identical host system.
So I fired up the MCP Server, hoping that there wouldn’t be any errors. (Okay, to be sincere, it took a few iterations in improvement to get it working with out errors… however I’m doing this weblog publish “cooking present model,” the place the boring work alongside the way in which is hidden. 😉
python netai-mcp-hello-world.py ╭─ FastMCP 2.0 ──────────────────────────────────────────────────────────────╮ │ │ │ _ __ ___ ______ __ __ _____________ ____ ____ │ │ _ __ ___ / ____/___ ______/ /_/ |/ / ____/ __ |___ / __ │ │ _ __ ___ / /_ / __ `/ ___/ __/ /|_/ / / / /_/ / ___/ / / / / / │ │ _ __ ___ / __/ / /_/ (__ ) /_/ / / / /___/ ____/ / __/_/ /_/ / │ │ _ __ ___ /_/ __,_/____/__/_/ /_/____/_/ /_____(_)____/ │ │ │ │ │ │ │ │ 🖥️ Server title: FastMCP │ │ 📦 Transport: Streamable-HTTP │ │ 🔗 Server URL: http://127.0.0.1:8002/mcp/ │ │ │ │ 📚 Docs: https://gofastmcp.com │ │ 🚀 Deploy: https://fastmcp.cloud │ │ │ │ 🏎️ FastMCP model: 2.10.5 │ │ 🤝 MCP model: 1.11.0 │ │ │ ╰────────────────────────────────────────────────────────────────────────────╯ [07/18/25 14:03:53] INFO Beginning MCP server 'FastMCP' with transport 'http' on http://127.0.0.1:8002/mcp/server.py:1448 INFO: Began server course of [63417] INFO: Ready for software startup. INFO: Software startup full. INFO: Uvicorn working on http://127.0.0.1:8002 (Press CTRL+C to give up)
The following step was to configure LMStudio to behave because the MCP Consumer and connect with the server to have entry to the brand new “send_show_command” instrument. Whereas not “standardized, “most MCP Purchasers use a really frequent JSON configuration to outline the servers. LMStudio is certainly one of these purchasers.
Wait… when you’re questioning, ‘Wright here’s the community, Hank? What system are you sending the ‘present instructions’ to?’ No worries, my inquisitive buddy: I created a quite simple Cisco Modeling Labs (CML) topology with a few IOL units configured for direct SSH entry utilizing the PATty function.
Let’s see it in motion!
Okay, I’m positive you might be able to see it in motion. I do know I positive was as I used to be constructing it. So let’s do it!
To start out, I instructed the LLM on how to connect with my community units within the preliminary message.
I did this as a result of the pyATS instrument wants the deal with and credential info for the units. Sooner or later I’d like to have a look at the MCP servers for various supply of reality choices like NetBox and Vault so it could possibly “look them up” as wanted. However for now, we’ll begin easy.
First query: Let’s ask about software program model information.
You may see the main points of the instrument name by diving into the enter/output display screen.
That is fairly cool, however what precisely is going on right here? Let’s stroll by the steps concerned.
- The LLM consumer begins and queries the configured MCP servers to find the instruments obtainable.
- I ship a “immediate” to the LLM to contemplate.
- The LLM processes my prompts. It “considers” the totally different instruments obtainable and in the event that they is perhaps related as a part of constructing a response to the immediate.
- The LLM determines that the “send_show_command” instrument is related to the immediate and builds a correct payload to name the instrument.
- The LLM invokes the instrument with the right arguments from the immediate.
- The MCP server processes the referred to as request from the LLM and returns the outcome.
- The LLM takes the returned outcomes, together with the unique immediate/query as the brand new enter to make use of to generate the response.
- The LLM generates and returns a response to the question.
This isn’t all that totally different from what you may do when you have been requested the identical query.
- You’d contemplate the query, “What software program model is router01 working?”
- You’d take into consideration the alternative ways you could possibly get the knowledge wanted to reply the query. Your “instruments,” so to talk.
- You’d resolve on a instrument and use it to collect the knowledge you wanted. Most likely SSH to the router and run “present model.”
- You’d overview the returned output from the command.
- You’d then reply to whoever requested you the query with the right reply.
Hopefully, this helps demystify slightly about how these “AI Brokers” work beneath the hood.
How about yet another instance? Maybe one thing a bit extra advanced than merely “present model.” Let’s see if the NetAI agent will help establish which change port the host is linked to by describing the essential course of concerned.
Right here’s the query—sorry, immediate, that I undergo the LLM:
What we must always discover about this immediate is that it’ll require the LLM to ship and course of present instructions from two totally different community units. Identical to with the primary instance, I do NOT inform the LLM which command to run. I solely ask for the knowledge I would like. There isn’t a “instrument” that is aware of the IOS instructions. That data is a part of the LLM’s coaching knowledge.
Let’s see the way it does with this immediate:
And take a look at that, it was in a position to deal with the multi-step process to reply my query. The LLM even defined what instructions it was going to run, and the way it was going to make use of the output. And when you scroll again as much as the CML community diagram, you’ll see that it accurately identifies interface Ethernet0/2 because the change port to which the host was linked.
So what’s subsequent, Hank?
Hopefully, you discovered this exploration of agentic AI instrument creation and experimentation as fascinating as I’ve. And perhaps you’re beginning to see the chances to your personal each day use. When you’d prefer to attempt a few of this out by yourself, you will discover every part you want on my netai-learning GitHub challenge.
- The mcp-pyats code for the MCP Server. You’ll discover each the easy “hey world” instance and a extra developed work-in-progress instrument that I’m including extra options to. Be happy to make use of both.
- The CML topology I used for this weblog publish. Although any community that’s SSH reachable will work.
- The mcp-server-config.json file that you could reference for configuring LMStudio
- A “System Immediate Library” the place I’ve included the System Prompts for each a primary “Mr. Packets” community assistant and the agentic AI instrument. These aren’t required for experimenting with NetAI use instances, however System Prompts could be helpful to make sure the outcomes you’re after with LLM.
A few “gotchas” I wished to share that I encountered throughout this studying course of, which I hope may prevent a while:
First, not all LLMs that declare to be “skilled for instrument use” will work with MCP servers and instruments. Or at the least those I’ve been constructing and testing. Particularly, I struggled with Llama 3.1 and Phi 4. Each appeared to point they have been “instrument customers,” however they did not name my instruments. At first, I believed this was resulting from my code, however as soon as I switched to Gemma 2, they labored instantly. (I additionally examined with Qwen3 and had good outcomes.)
Second, when you add the MCP Server to LMStudio’s “mcp.json” configuration file, LMStudio initiates a connection and maintains an energetic session. Which means when you cease and restart the MCP server code, the session is damaged, providing you with an error in LMStudio in your subsequent immediate submission. To repair this problem, you’ll must both shut and restart LMStudio or edit the “mcp.json” file to delete the server, put it aside, after which re-add it. (There may be a bug filed with LMStudio on this drawback. Hopefully, they’ll repair it in an upcoming launch, however for now, it does make improvement a bit annoying.)
As for me, I’ll proceed exploring the idea of NetAI and the way AI brokers and instruments could make our lives as community engineers extra productive. I’ll be again right here with my subsequent weblog as soon as I’ve one thing new and fascinating to share.
Within the meantime, how are you experimenting with agentic AI? Are you excited in regards to the potential? Any ideas for an LLM that works effectively with community engineering data? Let me know within the feedback beneath. Speak to you all quickly!
Join Cisco U. | Be a part of the Cisco Studying Community as we speak totally free.
Study with Cisco
X | Threads | Fb | LinkedIn | Instagram | YouTube
Use #CiscoU and #CiscoCert to hitch the dialog.
Share:
