Hey there, everybody, and welcome to the newest installment of “Hank shares his AI journey.” 🙂 Synthetic Intelligence (AI) continues to be all the craze, and getting back from Cisco Dwell in San Diego, I used to be excited to dive into the world of agentic AI.
With bulletins like Cisco’s personal agentic AI answer, 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 study 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 gained’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, nevertheless it begins to work extra independently. Pushed by the targets we set, and using entry to instruments and programs we offer, an agentic AI answer 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 needed 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 knowledge. An LLM can “perceive” your questions and directions. On its personal, nonetheless, the LLM is restricted to the info it was skilled on. It could possibly’t even search the online for present film showtimes with out some “device” permitting it to carry out an online 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 device’s objective. However just lately, a brand new framework for constructing AI instruments has gotten a whole lot of pleasure and is beginning to turn into a brand new “customary” for device growth.
This framework is named the Mannequin Context Protocol (MCP). Initially developed by Anthropic, the corporate behind Claude, any developer to make use of MCP to construct instruments, known as “MCP Servers,” and any AI platform can act as an “MCP Shopper” 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 device constructing. So I figured I’d dig in and determine how MCP works by constructing my very own very fundamental NetAI Agent.
I’m removed from the primary networking engineer to wish to dive into this area, 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 subjects, 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 an area NetAI playground lab
There isn’t a scarcity of AI instruments and platforms in the present day. There may be ChatGPT, Claude, Mistral, Gemini, and so many extra. Certainly, I make the most of lots of them frequently for numerous AI duties. Nevertheless, for experimenting with agentic AI and AI instruments, I needed one thing that was 100% native and didn’t depend on a cloud-connected service.
A main motive for this want was that I needed to make sure all of my AI interactions remained totally on my pc and inside my community. I knew I might be experimenting in a wholly new space of growth. 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 thought of leveraging cloud-based AI programs. I might really feel freer to be taught and make errors if I knew the chance 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 potential choices able to go. The primary is Ollama, a robust open-source engine for operating LLMs domestically, or a minimum of 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. After I learn a current weblog by LMStudio about MCP help now being included, I made a decision to present it a attempt for my experimentation.
LMStudio is a consumer for operating LLMs, nevertheless it isn’t an LLM itself. It gives entry to a lot of LLMs out there for obtain and operating. With so many LLM choices out there, it may be overwhelming whenever you get began. The important thing issues for this weblog put up and demonstration are that you just want a mannequin that has been skilled for “device 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 subsequent factor I wanted for my experimentation was an preliminary thought for a device to construct. After some thought, I made a decision a superb “hey world” for my new NetAI undertaking can be a method for AI to ship and course of “present instructions” from a community gadget. I selected pyATS to be my NetDevOps library of alternative for this undertaking. Along with being a library that I’m very conversant in, it has the good thing about computerized output processing into JSON by means of the library of parsers included in pyATS. I might additionally, inside simply a few minutes, generate a fundamental Python operate to ship a present command to a community gadget 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: Elective[str] = "ios",
) -> Elective[Dict[str, Any]]:
# Construction a dictionary for the gadget configuration that may be loaded by PyATS
device_dict = {
"gadgets": {
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)
gadget = testbed.gadgets[device_name]
gadget.join()
output = gadget.parse(command)
gadget.disconnect()
return output
Between Kareem’s weblog posts and the getting-started information for FastMCP 2.0, I realized it was frighteningly straightforward to transform my operate into an MCP Server/Instrument. I simply wanted so as to add 5 strains of code.
from fastmcp import FastMCP
mcp = FastMCP("NetAI Whats up World")
@mcp.device()
def send_show_command()
.
.
if __name__ == "__main__":
mcp.run()
Properly.. it was ALMOST that straightforward. I did must make just a few changes to the above fundamentals to get it to run efficiently. You possibly can see the full working copy of the code in my newly created NetAI-Studying undertaking on GitHub.
As for these few changes, the modifications I made have been:
- A pleasant, detailed docstring for the operate behind the device. MCP purchasers use the small print from the docstring to know how and why to make use of the device.
- After some experimentation, I opted to make use of “http” transport for the MCP server fairly than the default and extra frequent “STDIO.” The explanation I went this fashion was to organize for the following section of my experimentation, when my pyATS MCP server would doubtless run throughout the community lab surroundings itself, fairly than on my laptop computer. STDIO requires the MCP Shopper 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 growth to get it working with out errors… however I’m doing this weblog put up “cooking present model,” the place the boring work alongside the best way is hidden. 😉
python netai-mcp-hello-world.py ╭─ FastMCP 2.0 ──────────────────────────────────────────────────────────────╮ │ │ │ _ __ ___ ______ __ __ _____________ ____ ____ │ │ _ __ ___ / ____/___ ______/ /_/ |/ / ____/ __ |___ / __ │ │ _ __ ___ / /_ / __ `/ ___/ __/ /|_/ / / / /_/ / ___/ / / / / / │ │ _ __ ___ / __/ / /_/ (__ ) /_/ / / / /___/ ____/ / __/_/ /_/ / │ │ _ __ ___ /_/ __,_/____/__/_/ /_/____/_/ /_____(_)____/ │ │ │ │ │ │ │ │ 🖥️ Server identify: 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 operating on http://127.0.0.1:8002 (Press CTRL+C to stop)
The subsequent step was to configure LMStudio to behave because the MCP Shopper and hook up with the server to have entry to the brand new “send_show_command” device. Whereas not “standardized, “most MCP Shoppers use a really frequent JSON configuration to outline the servers. LMStudio is one in all these purchasers.
Wait… for those who’re questioning, ‘Wright here’s the community, Hank? What gadget 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 gadgets configured for direct SSH entry utilizing the PATty characteristic.
Let’s see it in motion!
Okay, I’m certain you might be able to see it in motion. I do know I certain was as I used to be constructing it. So let’s do it!
To start out, I instructed the LLM on how to hook up with my community gadgets within the preliminary message.
I did this as a result of the pyATS device wants the deal with and credential data for the gadgets. 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 will probably “look them up” as wanted. However for now, we’ll begin easy.
First query: Let’s ask about software program model information.
You possibly can see the small print of the device name by diving into the enter/output display screen.
That is fairly cool, however what precisely is occurring right here? Let’s stroll by means of the steps concerned.
- The LLM consumer begins and queries the configured MCP servers to find the instruments out there.
- I ship a “immediate” to the LLM to think about.
- The LLM processes my prompts. It “considers” the completely different instruments out there and in the event that they could be related as a part of constructing a response to the immediate.
- The LLM determines that the “send_show_command” device is related to the immediate and builds a correct payload to name the device.
- The LLM invokes the device with the right arguments from the immediate.
- The MCP server processes the known as request from the LLM and returns the end result.
- 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 completely different from what you may do for those who have been requested the identical query.
- You’d contemplate the query, “What software program model is router01 operating?”
- You’d take into consideration the alternative ways you would get the data wanted to reply the query. Your “instruments,” so to talk.
- You’d resolve on a device and use it to assemble the data you wanted. In all probability SSH to the router and run “present model.”
- You’d evaluate the returned output from the command.
- You’d then reply to whoever requested you the query with the right reply.
Hopefully, this helps demystify a bit about how these “AI Brokers” work below 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 determine which swap 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’s going to require the LLM to ship and course of present instructions from two completely different community gadgets. Similar to with the primary instance, I do NOT inform the LLM which command to run. I solely ask for the data I would like. There isn’t a “device” 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 for those who scroll again as much as the CML community diagram, you’ll see that it appropriately identifies interface Ethernet0/2 because the swap port to which the host was linked.
So what’s subsequent, Hank?
Hopefully, you discovered this exploration of agentic AI device creation and experimentation as fascinating as I’ve. And perhaps you’re beginning to see the probabilities on your personal each day use. In case you’d prefer to attempt a few of this out by yourself, yow will discover the whole lot you want on my netai-learning GitHub undertaking.
- The mcp-pyats code for the MCP Server. You’ll discover each the easy “hey world” instance and a extra developed work-in-progress device that I’m including extra options to. Be at liberty to make use of both.
- The CML topology I used for this weblog put up. Although any community that’s SSH reachable will work.
- The mcp-server-config.json file you can reference for configuring LMStudio
- A “System Immediate Library” the place I’ve included the System Prompts for each a fundamental “Mr. Packets” community assistant and the agentic AI device. These aren’t required for experimenting with NetAI use circumstances, however System Prompts could be helpful to make sure the outcomes you’re after with LLM.
A few “gotchas” I needed 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 device use” will work with MCP servers and instruments. Or a minimum of those I’ve been constructing and testing. Particularly, I struggled with Llama 3.1 and Phi 4. Each appeared to point they have been “device customers,” however they didn’t name my instruments. At first, I believed this was as a result of 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. Because of this for those who cease and restart the MCP server code, the session is damaged, supplying you with an error in LMStudio in your subsequent immediate submission. To repair this subject, you’ll have to 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 growth 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 concerning the potential? Any recommendations for an LLM that works properly with community engineering data? Let me know within the feedback beneath. Discuss to you all quickly!
Join Cisco U. | Be part of the Cisco Studying Community in the present day totally free.
Study with Cisco
X | Threads | Fb | LinkedIn | Instagram | YouTube
Use #CiscoU and #CiscoCert to hitch the dialog.
Share:
