MCP for DevOps – Collection Opener and MCP Structure Intro
You’ve gotten undoubtedly heard about Anthropic’s MCP (Mannequin Context Protocol) open supply mission. Should you haven’t, I hope your trip on a distant island with out web entry was beautiful!
As a die-hard YouTube Premium fan, I’m inundated with video suggestions with themes like “What’s MCP?” “OMG, This Modifications All the pieces,” and my favourite, “Goodbye Builders, MCP is Right here to Keep.” Critically? Whereas it’s a incredible mission, it isn’t right here to switch us.
Over the following a number of weeks, I’ll delve into these subjects:
MCP—Why Ought to You Care?: This can present a quick overview of MCP from a communication, discovery, and interplay perspective. We are going to then discover what it appears like on the wire and the way it features as a consumer/server structure, adopted by varied use circumstances. I gained’t cowl the historical past of MCP or different important info, as numerous wonderful assets can be found on YouTube, dev.to, Medium, and elsewhere.
MCP for DevOps: I’ll focus on a choice of use circumstances that work effectively for DevOps, NetOps, and SecOps roles.
MCP How-to: That is the place issues get thrilling. I’ll current a number of demos and walk-throughs for the next use circumstances:
- Cursor with GitHub: Use Cursor as an MCP consumer to programmatically work together with an MCP server that integrates with GitHub for a Cisco DevOps workflow
- Cursor with Argo CD: Use Cursor as an MCP consumer to programmatically work together with an MCP server that employs Argo CD for a Cisco DevOps workflow
- Claude Desktop & DevOps Workflows: We are going to swap issues up through the use of Claude Desktop as an alternative of Cursor to show flexibility on the MCP consumer aspect
On the finish of the collection, I’ll tie all of this collectively to indicate how Cursor, with a number of MCP shoppers, can drive adjustments to Ansible playbooks in a GitHub repository, triggering actions within the Argo CD workflow. In the end, we’ll use the Ansible playbook to switch configuration settings on Cisco options akin to Cisco ISE (Id Companies Engine) and different Cisco merchandise.
I hope you be part of me on this journey.
Let’s get began with discussing the MCP structure and why it is best to care about it.
MCP Intro—Why Ought to You Care?
Welcome to the primary submit in our three-part technical collection on Mannequin Context Protocol (MCP), a brand new, centered protocol constructed to assist AI functions and brokers work together with instruments, APIs, recordsdata, and databases constantly and programmatically.
Should you’re in DevOps and experimenting with AI-driven automation, MCP deserves your consideration—not as a silver bullet however as a sensible step towards cleaner integration between AI methods and your operational stack. That mentioned, it’s early days. MCP is new and transferring quick, and whereas it already solves plenty of real-world issues, there are nonetheless corners to shine and edge circumstances it doesn’t but cowl.
What’s MCP, and Why Does It Matter?
As illustrated in Determine 1, Mannequin Context Protocol (MCP) is a protocol that gives a uniform method to plug in an AI mannequin into instruments and companies.
Determine 1. MCP with LLMs and Instruments
It’s:
- A light-weight communication protocol designed particularly for AI brokers and functions.
- Constructed to attach these brokers to instruments, APIs, databases, and file methods.
- Structured as a consumer/server structure—easy and predictable.
- Plumbing
It’s not:
- A messaging protocol for agent-to-agent communication.
- An LLM, database, AI assistant or agent.
- A general-purpose integration platform.
- A alternative on your current APIs or information bus.
MCP’s job is tightly scoped: give an AI agent a clear, standardized method to uncover, request, and invoke capabilities on current tool-based infrastructure. In case your LLM-powered bot must name a REST API, listing recordsdata, or question a database—MCP supplies the glue.
MCP issues as a result of it reduces and, in lots of circumstances, removes the toil for AI functions and brokers to search out, hook up with, and leverage exterior instruments and companies akin to APIs, information sources, and different non-AI native device units. For Dev/Web/SecOps employees, it might carry instant worth so that you can leverage an AI agent to hook up with your current information sources and APIs in order that an operationally-focused agent can extra precisely full duties.
We are going to focus on use circumstances within the subsequent weblog, however think about you must create a workflow that works with Ansible Playbooks, NetBox, and GitHub and automate configurations in opposition to your infrastructure.
An instance workflow might seem like this:
- You manually create a Jinja2 template for Ansible and host it on GitHub.
- Collect information out of your NetBox deployment.
- You utilize Python + Jinja2 to populate the playbook template with information from NetBox after which invoke Ansible by way of a Python module, CLI, runner, and so forth.
- Ideally, you employ a CI/CD device to auto-run this workflow.
Quick ahead from the nice ’ole days; you or somebody in your group study in regards to the energy of AI Brokers and create a collection of AI brokers that may faucet into every device and information supply with out writing any code. They will leverage MCP to hook up with every useful resource as MCP servers and work together with them natively—no particular script code. No scouring the web for SDKs or some mysterious script somebody recommends that you simply don’t perceive. To me, that is one in every of many value-add use circumstances of MCP.
Overview of MCP – Structure and Core Elements
MCP has a streamlined structure and there aren’t many transferring elements.
As illustrated in Determine 2 MCP makes use of a consumer/server structure. Let’s outline what the consumer and server elements do.
Determine 2. MCP Elements
Determine 2 reveals an MCP host which is an AI utility akin to an AI agent, IDE, coding assistant, and so forth..
The MCP consumer (MCP-C) is software program that runs on MCP hosts and has one-to-one connections to MCP servers (MCP-S).
The MCP server is software program that represents particular service or device capabilities.
The MCP host makes use of the language-specific MCP SDK for consumer connections (instance: MCP Python SDK) to ascertain connections to MCP servers. The MCP SDK is used for each client-side and server-side code.
Instance Python MCP consumer code.
Instance Python MCP server code.
Many present MCP shoppers are full functions or AI brokers with the MCP consumer SDK performance natively inbuilt. You possibly can see an instance listing right here: https://modelcontextprotocol.io/shoppers
There are quite a few sources of MCP server lists on the Web. Here’s a listing from the MCP mission: https://modelcontextprotocol.io/examples. Some MCP consumer suppliers, akin to Cursor, have their very own listing of servers: https://cursor.listing/.
Determine 2 reveals that every MCP-C occasion has a one-to-one connection to every MCP-S occasion. Within the determine, there are two MCP shoppers operating on the MCP host, an AI agent on this instance. The primary MCP consumer is connecting to a locally-hosted MCP server that gives native machine file system entry. The second MCP consumer is connecting to a remotely hosted MCP server that’s offering entry to a distant file system.
MCP shoppers trade messages with MCP servers utilizing JSON-RPC 2.0 (because the wire format). For native information sources, MCP makes use of JSON-RPC over stdio (Normal Enter/Output) because the transport. Determine 3., illustrates how an MCP-C connects to a neighborhood MCP-S for file or DB entry utilizing stdio. The MCP-S sends JSON-RPC messages to its commonplace output / stdout and reads from the usual enter / stdin.
Determine 3. JSON-RPC over stdio
Right here is an instance of operating an MCP filesystem server domestically in stdio mode and proscribing entry to a really particular listing:
npx -y @modelcontextprotocol/server-filesystem /Customers/shmcfarl/code/mcp-testing Safe MCP Filesystem Server operating on stdio Allowed directories: [ '/Users/shmcfarl/code/mcp-testing' ]
Utilizing an ideal check device such because the MCP Inspector you’ll be able to pair a neighborhood consumer (MCP Inspector) together with your domestically operating stdio or HTTP+SSE server:
npx -y @modelcontextprotocol/inspector npx -y @modelcontextprotocol/server-filesystem /Customers/shmcfarl/code/mcp-testing
Beginning MCP inspector...
Proxy server listening on port 3000
MCP Inspector is up and operating at http://localhost:5173
Question parameters: {
transportType: 'stdio',
command: 'npx',
args: '-y @modelcontextprotocol/server-filesystem -y /Customers/shmcfarl/code/mcp-testing',
. . . [Output removed for clarity]
Spawned stdio transport
Linked MCP consumer to backing server transport
Created internet app transport
Created internet app transport
Arrange MCP proxy
Acquired message for sessionId 697bd02d-5d67-4dfc-85b9-6a12d6a99f45
Acquired message for sessionId 697bd02d-5d67-4dfc-85b9-6a12d6a99f45
Acquired message for sessionId 697bd02d-5d67-4dfc-85b9-6a12d6a99f45
Acquired message for sessionId 697bd02d-5d67-4dfc-85b9-6a12d6a99f45
MCP helps HTTP+SSE (Server-Despatched Occasions) to ship structured requests from service backends utilizing MCP servers to MCP shoppers for native or distant connections. The 2025-03-26 specification adjustments states that MCP is transferring to a extra versatile Streamable HTTP transport. Nonetheless, HTTP+SSE transport can nonetheless be used for backward compatibility. This retains it clear, traceable, and tool-agnostic. Word: As of the time of scripting this weblog, the brand new Streaming HTTP help isn’t accomplished in every SDK.
Determine 4 illustrates the connection circulation for HTTP+SSE eventualities. Within the determine, HTTP POST is used for MCP-C -to- MCP-S messages. HTTP+SSE is used for MCP-S -to- MCP-C messages.
Determine 4. MCP-C -to- MCP-S communication utilizing HTTP+SSE
You possibly can undergo the MCP quickstart server and consumer guides to discover ways to setup your personal climate consumer/server combo: https://modelcontextprotocol.io/quickstart/server. Utilizing an identical setup, you’ll be able to see some HTTP messages for stuff like a instruments listing name:
POST /messages/?session_id=6ccde3779adf43cc9d3f5f661508310b HTTP/1.1
Host: 0.0.0.0:8080
Settle for: */*
Settle for-Encoding: gzip, deflate
Connection: keep-alive
Consumer-Agent: python-httpx/0.28.1
Content material-Size: 46
Content material-Sort: utility/json
{"methodology":"instruments/listing","jsonrpc":"2.0","id":2}
HTTP/1.1 202 Accepted
date: Tue, 08 Apr 2025 20:14:51 GMT
server: uvicorn
content-length: 8
Accepted
And a device name to get the climate forecast:
POST /messages/?session_id=6ccde3779adf43cc9d3f5f661508310b HTTP/1.1
Host: 0.0.0.0:8080
Settle for: */*
Settle for-Encoding: gzip, deflate
Connection: keep-alive
Consumer-Agent: python-httpx/0.28.1
Content material-Size: 134
Content material-Sort: utility/json
{"methodology":"instruments/name","params":{"identify":"get_forecast","arguments":{"latitude":39.7392,"longitude":-104.9903}},"jsonrpc":"2.0","id":3}
HTTP/1.1 202 Accepted
date: Tue, 08 Apr 2025 20:14:54 GMT
server: uvicorn
content-length: 8
Accepted
And a response for the climate forecast immediate I entered for Denver, CO:
occasion: message
information: {"jsonrpc":"2.0","id":3,"outcome":{"content material":[{"type":"text","text":"nThis Afternoon:nTemperature: 74..FnWind: 12 mph WnForecast: Partly sunny. High near 74, with temperatures falling to around 72 in the afternoon. West wind around 12 mph, with gusts as high as 18 mph.nn---nnTonight:nTemperature: 42..FnWind: 5 to 10 mph WSWnForecast: Partly cloudy, with a low around 42. West southwest wind 5 to 10 mph, with gusts as high as 18 mph.nn---nnWednesday:nTemperature: 71..FnWind: 5 to 15 mph WnForecast: Mostly sunny, with a high near 71. West wind 5 to 15 mph, with gusts as high as 24 mph.nn---nnWednesday Night:nTemperature: 40..FnWind: 2 to 14 mph WNWnForecast: Mostly clear, with a low around 40. West northwest wind 2 to 14 mph, with gusts as high as 29 mph.nn---nnThursday:nTemperature: 68..FnWind: 2 to 8 mph ESEnForecast: Sunny, with a high near 68. East southeast wind 2 to 8 mph, with gusts as high as 16 mph.n"}],"isError":false}}
For the reason that specification change to Streamable HTTP could be very latest and never totally carried out as of the writing of this weblog, I’ll forgo doing a granular clarification of that connection sequence. I beneficial that you simply learn in regards to the proposed Streamable HTTP implementation right here: https://modelcontextprotocol.io/specification/2025-03-26/primary/transports#streamable-http.
Discovery
When an agent must work together with a device or service, MCP supplies a useful resource discovery mechanism that lets MCP shoppers uncover out there assets. The MCP consumer can use direct assets or useful resource templates. You possibly can learn extra in regards to the useful resource discovery choices at https://modelcontextprotocol.io/docs/ideas/assets. However, the necessary factor to know is that the aim of useful resource discovery is to search out out the next info:
- Supported capabilities and actions
- Protocol variations
- Customized metadata
Determine 5 reveals the MCP-C to MCP-S request/response circulation for the capabilities discovery.
Determine 5. MCP Discovery Stream
Whereas there isn’t a MCP server registry that MCP shoppers can search to dynamically uncover all out there MCP servers and their capabilities, there are MCP server directories as was famous early within the doc. There’s an ever-growing variety of MCP directories and in lots of circumstances, all of them have the identical or comparable listing of MCP servers. A number of of the numerous websites embrace:
MCP Useful resource Discovery – Instance
Let’s take a look at an instance of useful resource discovery utilizing direct assets.
I’ve the SQLite MCP Server operating on my native machine. I’m utilizing Claude Desktop as my AI utility with the MCP consumer performance configured to make use of the SQLite MCP server. Here’s a snippet from my claude_desktop_config.json file:
"mcpServers": {
"sqlite": {
"command": "uvx",
"args": ["mcp-server-sqlite", "--db-path", "/Users/shmcfarl/code/mcp-testing/sqlite/test.db"]
},
Once I use Claude Desktop to device name SQLite and ask for an inventory of server assets, you’ll be able to see the message trade from the MCP consumer to MCP server.
2025-04-09T18:08:37.964Z [sqlite] [info] Message from consumer: {"methodology":"assets/listing","params":{},"jsonrpc":"2.0","id":44}
2025-04-09T18:08:37.965Z [sqlite] [info] Message from server: {"jsonrpc":"2.0","id":44,"outcome":{"assets":[{"uri":"memo://insights","name":"Business Insights Memo","description":"A living document of discovered business insights","mimeType":"text/plain"}]}}
Per the MCP specification you’ll be able to see the tactic utilized by the MCP consumer is assets/listing and the MCP server responds utilizing the direct assets format:
{
uri: string; // Distinctive identifier for the useful resource
identify: string; // Human-readable identify
description?: string; // Elective description
mimeType?: string; // Elective MIME sort
}
Conclusion
MCP is off to a robust begin, particularly for DevOps groups experimenting with AI-driven automation.
On the identical time, it’s nonetheless a younger protocol. MCP provides you a clear basis if you happen to’re constructing AI-enabled workflows that must work together with infrastructure and instruments safely—however you’ll nonetheless must assess match on your particular use case.
There’s much more introductory content material that I may cowl, however I believe this lays a basis for the remainder of the weblog collection. For the rest of the blogs it’s important so that you can know:
MCP is good for:
- Brokers want to hook up with a number of information sources and companies in a typical manner
- It abstracts away the per-integration code complexity – simply use the MCP SDK
- You want it for a low toil platform or with IDE integrations
What doesn’t MCP do (a minimum of right this moment)?
- MCP isn’t an agent-to-agent framework
- MCP isn’t used for the creation, deployment, lifecycle administration, and safety of brokers or instruments
- MCP isn’t an LLM
- MCP isn’t an information supply
- MCP doesn’t dynamically uncover instruments and companies the MCP server will characterize
We additionally discovered how MCP shoppers and servers work together with each other and over which varieties of protocol and messaging codecs.
Let’s cease there and decide again up within the subsequent weblog on MCP for DevOps: Use Circumstances
Want to see it in motion? Watch the complete MCP for DevOps: Structure & Elements video walkthrough right here: https://youtu.be/Qdms0EHwhOw
Subsequent within the collection
MCP for DevOps: Use Circumstances
✅ AI Brokers Triggering DevOps Instruments Use MCP to work together with current DevOps scripts, APIs, or companies in a typical format an AI agent can devour.
✅ Infrastructure-Conscious LLMs Let your AI apps ask structured questions like “What kubernetes companies are operating in namespace default?” or “Create a brand new database desk”—with stay solutions from methods by way of MCP servers.
✅ Safe Software Invocation by way of AI expose choose CLI instruments or automation workflows by way of an MCP server interface, permitting AI brokers to work together with them underneath managed situations akin to utilizing a Docker scout MCP to scan photos.
See you on the subsequent submit!
Share:
