Mannequin Context Protocol (MCP) servers present a brand new method to unify automation and observability throughout hybrid Cisco environments. They allow an AI shopper to routinely uncover and use instruments throughout a number of Catalyst Middle clusters and Meraki organizations.
When you’re inquisitive about how this works, now’s the time to see it in motion.
On this new demo, Cisco Principal Technical Advertising Engineer Gabi Zapodeanu exhibits how a single AI shopper routes natural-language queries to the suitable instrument, retrieves responses from a number of domains, and helps you troubleshoot or report in your community extra effectively.
Watch the total replay:
See MCP in Motion: Catalyst Middle and Meraki Integration
Within the video, Gabi demonstrates how MCP servers allow an AI shopper to work together with instruments throughout a number of platforms. You’ll study:
- How the shopper connects to a number of MCP servers—one for Catalyst Middle, one for Meraki—and discovers out there instruments from each.
- How these instruments are chosen and executed in actual time primarily based on person intent.
- How a single question can span clusters and organizations utilizing patterns like cluster = all.
The session consists of sensible walkthroughs of multi-cluster stock lookups, problem correlation throughout, and a BGP troubleshooting workflow constructed from primary instruments.
Understanding MCP Structure and Workflow
MCP makes use of a client-server protocol that allows an AI assistant to connect with a number of MCP servers and dynamically uncover out there instrument definitions. Here’s what the total workflow seems like:
- An AI shopper, powered by a big language mannequin, connects to a number of MCP servers.
- Every server gives a listing of instruments—both prebuilt runbooks or auto-generated APIs.
- A person asks a query; the AI shopper selects the suitable instrument, fills within the parameters, and sends the request.
- The instruments execute, return knowledge, and the AI responds to the person.
This allows asking a single query—resembling “The place is that this shopper linked?”—and receiving solutions from a number of clusters and organizations.
Crucial Instruments vs. Declarative Instruments in MCP Servers
The demo explains two varieties of instruments supported by MCP servers:
- Crucial instruments are predefined sequences written in Ansible, Terraform, or Python. They’re finest fitted to write duties the place guardrails and strict execution order are essential.
- Declarative instruments are auto-generated from YAML information and are perfect for read-heavy duties resembling stock, occasion lookup, or compliance checks. In addition they help pagination with offset and restrict parameters.
Gabi shares examples of each varieties, demonstrating their use in actual situations like firmware checks and cross-domain shopper discovery.
Troubleshooting and Compliance Utilizing Generative AI Flows
Past single-tool calls, MCP helps multi-step workflows. These generative AI flows allow you to:
- Correlate occasions
- Determine root causes of points resembling BGP flaps
- Run compliance checks or accumulate telemetry throughout websites
- Apply guardrails for modifications, guaranteeing solely trusted runbooks are used for configuration actions
The MCP shopper learns from instrument utilization patterns and may recommend new instruments primarily based on frequent API calls.
The right way to Get Began and What’s Subsequent
This demo gives a transparent, sensible introduction to MCP for anybody working in NetOps or DevOps. You’ll acquire a greater understanding of:
- Why MCP issues at the moment
- The right way to join MCP to your Cisco platforms
- The varieties of instruments and workflows it helps
- The right way to construction your individual instruments utilizing YAML or SDKs
Watch the total session:
Subscribe to Cisco DevNet on YouTube to get notified when new demos go reside.
