Wrangling the Wild West of MCP Servers

[ad_1] 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 truly construct considered one of 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 likelihood is that you have already got what you want.

Enter: OpenAPI spec OpenAPI is a pleasant contract in your APIs. You would possibly’ve used it for Swagger docs, SDKs, Postman collections, or that one dusty codegen undertaking from 2021. However right here’s the twist: What should you 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 just some strains of Python and a FastMCP wrapper round your OpenAPI file. The magic? Your APIs get remodeled into secure, role-based AI instruments—with out writing a single customized software 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 good On this new AI-powered world, pace is the simple half. Governance—that’s the tougher raise.

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 checklist of patterns (regex for individuals who love ache and struggling) and HTTP verbs, you'll be able to 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 “study” 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 way of a real-world use case.

Say you’re a NOC workforce managing a multi-site Meraki deployment. You’re liable for retaining community gadgets patched and safe—however you'll be able to’t simply schedule firmware upgrades at any time. Some websites are 24/7. Some spike at midday. Some run night time shifts. The perfect improve window is a transferring 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 workforce wants the agent to generate compliance studies. They should know which gadgets are operating outdated firmware—however they’re not scheduling upgrades or touching stay site visitors.

Two personas. Two very totally different scopes. One MCP server.

Right here’s the fantastic 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:

<img loading="lazy" decoding="async" class="aligncenter wp-image-476758 size-full" src="https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Role-Based-Route-Configurations-1.png" alt="Meraki MCP Server Role-Based Route Configurations" width="942" height="556" srcset="https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Role-Based-Route-Configurations-1-300x177.png 300w, https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Role-Based-Route-Configurations-1-768x453.png 768w, https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Role-Based-Route-Configurations-1.png 942w" sizes="auto, (max-width: 942px) 100vw, 942px"/> 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 do something. The magic is within the MCP server. The instruments turn into obtainable primarily based on the position, and the AI figures out the remainder.

That’s the sort of ruled autonomy that turns AI from a danger right into a functionality.

View it in motion As normal, you’ll discover every thing 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 selection) and sort the next immediate:

Your title is Community Pharaoh. You're performing with full administrative visibility and information entry privileges. You're a senior community administrator overseeing a number of Cisco Meraki organizations throughout the enterprise. Your position is to make sure that all community gadgets are operating the most recent compliant firmware. You're approved to advocate firmware upgrades, however you have to look ahead to express human approval earlier than initiating any updates.

Goal Organizations: Cisco U.

Activity Directions – For every group:

Listing all networks For every community, checklist all related gadgets (together with mannequin, serial, and present firmware model) Retrieve the obtainable firmware improve suggestions for the group Establish any machine that's not 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 inbuilt. The agent is aware of it may well’t act by itself—it should look ahead to approval. That’s governance baked into the immediate.

We didn’t inform the agent examine compliance or counsel upgrades. It makes use of the instruments obtainable by way of the MCP Server and acts throughout the boundaries outlined by its position.

The agent is doing clever work inside secure boundaries—utilizing solely what it’s been given entry to. No guesswork. No scraping. No uncontrolled API calls. Simply clear, policy-driven interplay by way of a structured, safe interface.

Right here’s what the MCP server config appears like behind the scenes:

<img loading="lazy" decoding="async" class="aligncenter wp-image-476759 size-full" src="https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Meraki-MCP-Server.png" alt="Cisco Meraki MCP Server Code" width="705" height="354" srcset="https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Meraki-MCP-Server-300x151.png 300w, https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Meraki-MCP-Server.png 705w" sizes="auto, (max-width: 705px) 100vw, 705px"/> 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 advocate firmware upgrades. Set it to “sysadmin” and the identical agent, with the identical immediate, will solely have the ability to generate compliance studies—no upgrades, no PUTs.

That’s the benefit of separating the intelligence (LLM) from the management aircraft (MCP). You keep in command of what the agent can do.

And right here’s what the MCP server makes occur:

Community Pharaoh traverses our Cisco U. group, pulling a listing of managed gadgets 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! <img loading="lazy" decoding="async" class="aligncenter wp-image-476755 size-full" src="https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Z703NEPm-NetworkPharoah3.png" alt="Cisco Meraki Dashboard" width="1359" height="713" srcset="https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Z703NEPm-NetworkPharoah3-300x157.png 300w, https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Z703NEPm-NetworkPharoah3-1024x537.png 1024w, https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Z703NEPm-NetworkPharoah3-768x403.png 768w, https://storage.googleapis.com/blogs-images-new/ciscoblogs/1/2025/08/Z703NEPm-NetworkPharoah3.png 1359w" sizes="auto, (max-width: 1359px) 100vw, 1359px"/>

The abilities behind the scenes Let’s zoom in for a second. What did it take to construct this?

Listed below are the abilities a community engineer must put this collectively:

Understanding of API fundamentals: OpenAPI specs, endpoints, HTTP strategies Python scripting: Spinning up a fundamental server and configuring the MCP wrapper Entry management pondering: Defining roles, entry boundaries, and imposing 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