Health & Wellness
Wrangling the Wild West of MCP Servers
Aug
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 several varieties:
“Okay, Kareem, this all sounds nice… however how do I really construct one in every 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 may’ve used it for Swagger docs, SDKs, Postman collections, or that one dusty codegen venture from 2021. However right here’s the twist: What in case 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” state of affairs. It’s only a few traces 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 software definition.
Think about the next instance:
You’re wrapping your present OpenAPI spec with FastMCP, wiring in your authenticated consumer, 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 straightforward half. Governance—that’s the tougher raise.
We don’t need to give the agent the keys to the dominion. We need to present it with a badge with simply the right entry.
That’s the place RouteMap is available in—our ACLs for AI. With a easy record of patterns (regex for many who love ache and struggling) and HTTP verbs, you may 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 must create an entire new auth system or practice 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 a real-world use case.
Say you’re a NOC crew managing a multi-site Meraki deployment. You’re accountable for maintaining community units patched and safe—however you may’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 shifting goal.
That’s the place the agent steps in.
You need to give the agent simply sufficient entry to assist:
- Pull the present firmware standing
- Monitor community utilization patterns
- Schedule upgrades when it is smart
In the meantime, your Sysadmin crew wants the agent to generate compliance reviews. They should know which units are working outdated firmware—however they’re not scheduling upgrades or touching stay visitors.
Two personas. Two very totally 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 change into obtainable based mostly on the position, 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 every little thing I’m displaying 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 working and our route maps outlined, I launch Claude Desktop (my MCP consumer 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 position is to make sure that all community units are working the newest compliant firmware. You’re licensed to advocate firmware upgrades, however you have to anticipate specific human approval earlier than initiating any updates.
Goal Organizations: Cisco U.
Activity Directions – For every group:
-
- Listing all networks
- For every community, record all related units (together with mannequin, serial, and present firmware model)
- Retrieve the obtainable firmware improve suggestions for the group
- Determine any gadget that’s not working the really useful model
- Suggest firmware upgrades as applicable
- Don’t carry out any improve except the human explicitly confirms with a press release like: “Sure, please improve [device/network].”
Just a few issues are value calling out:
The human-in-the-loop is inbuilt. The agent is aware of it can’t act by itself—it should anticipate approval. That’s governance baked into the immediate.
We didn’t inform the agent easy methods to examine compliance or recommend upgrades. It makes use of the instruments obtainable by the MCP Server and acts throughout the boundaries outlined by its position.
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 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 surroundings 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 be capable to generate compliance reviews—no upgrades, no PUTs.
That’s the benefit of separating the intelligence (LLM) from the management aircraft (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 based mostly on net search and schedules it for us based mostly on utilization.
- Et, voila!
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 implementing least privilege
- Agent design mindset: Prompting with context, goal, and clear human oversight
- Curiosity and experimentation: Making an attempt issues out and tweaking as you go
And perhaps most significantly:
- A shift in pondering—from constructing automation for the community, to constructing automation that understands the community.
Let’s preserve 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 as we speak without cost.
Study with Cisco
X | Threads | Fb | LinkedIn | Instagram | YouTube
Use #CiscoU and #CiscoCert to hitch the dialog.
Learn extra from the AI Break collection:
Share:
