It’s getting actual out right here.
Ever since I shared how autonomous AI Brokers can monitor and heal the community on their very own—sure, that one—I’ve gotten the identical follow-up query in numerous kinds:
“Okay, Kareem, this all sounds nice… however how do I really construct one in all these Mannequin Context Protocol (MCP) servers for my product?”
Excellent news! In case your product—like virtually each product on the market—has APIs, then chances are high that you have already got what you want.
Enter: OpenAPI spec
OpenAPI is a pleasant contract in your APIs. You may’ve used it for Swagger docs, SDKs, Postman collections, or that one dusty codegen undertaking from 2021. However right here’s the twist: What for those who handed that very same OpenAPI spec to your AI agent?
That’s it. That’s the important thing.
One OpenAPI spec → one MCP Server → one AI-powered, access-controlled gateway to your product.
And no, this isn’t a “12 steps and a DevRel miracle” scenario. It’s only a few strains of Python and a FastMCP wrapper round your OpenAPI file. The magic? Your APIs get remodeled into protected, role-based AI instruments—with out writing a single customized device definition.
Contemplate the next instance:
You’re wrapping your present OpenAPI spec with FastMCP, wiring in your authenticated shopper, and passing in your route-based ACLs. That’s how easy it’s to go from “API docs” to “AI-ready, access-controlled MCP server.”
Construct quick, govern sensible
On this new AI-powered world, velocity is the straightforward half. Governance—that’s the tougher carry.
We don’t wish to give the agent the keys to the dominion. We wish to present it with a badge with simply the correct entry.
That’s the place RouteMap is available in—our ACLs for AI. With a easy listing of patterns (regex for individuals who love ache and struggling) and HTTP verbs, you possibly can declare what endpoints are accessible for various personas (NOC, Sysadmin, full entry, and so forth).
Sure, it’s actually that straightforward. You’re constructing endpoint ACLs as code. You don’t have to create a complete new auth system or prepare a mannequin to “be taught” permissions. You simply declare what roles get entry to what endpoints—and the MCP Server enforces it.
From chaos to order
Let’s stroll by means of a real-world use case.
Say you’re a NOC crew managing a multi-site Meraki deployment. You’re liable for holding community units patched and safe—however you possibly can’t simply schedule firmware upgrades at any time. Some websites are 24/7. Some spike at midday. Some run evening shifts. The best improve window is a shifting goal.
That’s the place the agent steps in.
You wish to give the agent simply sufficient entry to assist:
- Pull the present firmware standing
- Monitor community utilization patterns
- Schedule upgrades when it is sensible
In the meantime, your Sysadmin crew wants the agent to generate compliance reviews. They should know which units are operating outdated firmware—however they’re not scheduling upgrades or touching dwell site visitors.
Two personas. Two very completely different scopes. One MCP server.
Right here’s the great thing about all of it. We didn’t write any customized instruments. We didn’t construct workflows or hardcode enterprise logic. We simply fed the MCP server the complete Meraki OpenAPI spec—and let RouteMap deal with the remainder:
The NOC agent can schedule upgrades, as a result of it wants that management. The Sysadmin agent? It will get a read-only view, tailor-made for visibility and compliance.
And once more—we didn’t inform the agent how to do something. The magic is within the MCP server. The instruments develop into accessible primarily based on the function, and the AI figures out the remainder.
That’s the form of ruled autonomy that turns AI from a danger right into a functionality.
View it in motion
As standard, you’ll discover the whole lot I’m exhibiting right here—the MCP server code, config, and immediate—in my GitHub Repo.
Now let’s hearth this factor up. (And, sure, Community Pharaoh is a factor now.)
With the MCP server operating and our route maps outlined, I launch Claude Desktop (my MCP shopper of alternative) and sort the next immediate:
Your identify is Community Pharaoh. You’re performing with full administrative visibility and knowledge entry privileges. You’re a senior community administrator overseeing a number of Cisco Meraki organizations throughout the enterprise. Your function is to make sure that all community units are operating the newest compliant firmware. You’re licensed to suggest firmware upgrades, however you could look forward to specific human approval earlier than initiating any updates.
Goal Organizations: Cisco U.
Process Directions – For every group:
- Record all networks
- For every community, listing all related units (together with mannequin, serial, and present firmware model)
- Retrieve the accessible firmware improve suggestions for the group
- Determine any machine that isn’t operating the advisable model
- Advocate firmware upgrades as applicable
- Don’t carry out any improve until the human explicitly confirms with an announcement like: “Sure, please improve [device/network].”
A couple of issues are value calling out:
The human-in-the-loop is in-built. The agent is aware of it can’t act by itself—it should look forward to approval. That’s governance baked into the immediate.
We didn’t inform the agent find out how to examine compliance or recommend upgrades. It makes use of the instruments accessible by means of the MCP Server and acts inside the boundaries outlined by its function.
The agent is doing clever work inside protected boundaries—utilizing solely what it’s been given entry to. No guesswork. No scraping. No uncontrolled API calls. Simply clear, policy-driven interplay by means of a structured, safe interface.
Right here’s what the MCP server config seems to be like behind the scenes:
Take note of the significance of the MCP_ROLE. This one atmosphere variable controls which routes the agent has entry to. Set it to “NOC” and the agent can suggest firmware upgrades. Set it to “sysadmin” and the identical agent, with the identical immediate, will solely be capable of generate compliance reviews—no upgrades, no PUTs.
That’s the benefit of separating the intelligence (LLM) from the management airplane (MCP). You keep answerable for what the agent can do.
And right here’s what the MCP server makes occur:
- Community Pharaoh traverses our Cisco U. group, pulling an inventory of managed units and spitting out a report.
- As Community Pharaoh is ready for a human within the loop to execute the improve, it additionally auto-corrects the model primarily based on internet search and schedules it for us primarily based on utilization.
- Et, voila!
The talents behind the scenes
Let’s zoom in for a second. What did it take to construct this?
Listed here are the talents a community engineer must put this collectively:
- Understanding of API fundamentals: OpenAPI specs, endpoints, HTTP strategies
- Python scripting: Spinning up a primary server and configuring the MCP wrapper
- Entry management considering: Defining roles, entry boundaries, and implementing least privilege
- Agent design mindset: Prompting with context, objective, and clear human oversight
- Curiosity and experimentation: Making an attempt issues out and tweaking as you go
And possibly most significantly:
- A shift in considering—from constructing automation for the community, to constructing automation that understands the community.
Let’s maintain pushing this frontier. As a result of the extra we construct clever boundaries, the extra we unlock protected autonomy.
And that’s how we go from the Wild West… to a well-governed AI-powered enterprise.
Join Cisco U. | Be a part of the Cisco Studying Community at this time without cost.
Be taught with Cisco
X | Threads | Fb | LinkedIn | Instagram | YouTube
Use #CiscoU and #CiscoCert to hitch the dialog.
Learn extra from the AI Break collection:
Share: