MCP for DevOps – Collection Opener and MCP Structure Intro

You’ve gotten undoubtedly heard about Anthropic’s MCP (Mannequin Context Protocol) open supply undertaking. If you happen to haven’t, I hope your trip on a distant island with out web entry was pretty!

As a die-hard YouTube Premium fan, I’m inundated with video suggestions with themes like “What’s MCP?” “OMG, This Adjustments All the things,” and my favourite, “Goodbye Builders, MCP is Right here to Keep.” Significantly? Whereas it’s a unbelievable undertaking, 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’ll then discover what it seems to be like on the wire and the way it features as a consumer/server structure, adopted by varied use instances. I received’t cowl the historical past of MCP or different important info, as numerous glorious sources can be found on YouTube, dev.to, Medium, and elsewhere.

MCP for DevOps: I’ll talk about a choice of use instances that work properly 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 instances:

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’ll change issues up by utilizing Claude Desktop as a substitute of Cursor to show flexibility on the MCP consumer facet

On the finish of the sequence, I’ll tie all of this collectively to point out how Cursor, with a number of MCP purchasers, can drive modifications to Ansible playbooks in a GitHub repository, triggering actions within the Argo CD workflow. In the end, we’ll use the Ansible playbook to change configuration settings on Cisco options resembling Cisco ISE (Identification Providers Engine) and different Cisco merchandise.

I hope you be a part of me on this journey.

Let’s get began with discussing the MCP structure and why you need to care about it.

MCP Intro—Why Ought to You Care?

Welcome to the primary submit in our three-part technical sequence 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.

If you happen to’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 stated, it’s early days. MCP is new and shifting quick, and whereas it already solves numerous real-world issues, there are nonetheless corners to shine and edge instances 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 providers.

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 isn’t:

A messaging protocol for agent-to-agent communication.
An LLM, database, AI assistant or agent.
A general-purpose integration platform.
A substitute on your present 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 present tool-based infrastructure. In case your LLM-powered bot must name a REST API, listing recordsdata, or question a database—MCP offers the glue.

MCP issues as a result of it reduces and, in lots of instances, removes the toil for AI functions and brokers to search out, connect with, and leverage exterior instruments and providers resembling APIs, information sources, and different non-AI native software units. For Dev/Web/SecOps employees, it may possibly deliver fast worth so that you can leverage an AI agent to connect with your present information sources and APIs in order that an operationally-focused agent can extra precisely full duties.

We’ll talk about use instances within the subsequent weblog, however think about you should create a workflow that works with Ansible Playbooks, NetBox, and GitHub and automate configurations in opposition to your infrastructure.

An instance workflow could appear to be this:

You manually create a Jinja2 template for Ansible and host it on GitHub.
Collect information out of your NetBox deployment.
You employ Python + Jinja2 to populate the playbook template with information from NetBox after which invoke Ansible through a Python module, CLI, runner, and so on.
Ideally, you utilize a CI/CD software to auto-run this workflow.

Quick ahead from the nice ’ole days; you or somebody in your group be taught concerning the energy of AI Brokers and create a sequence of AI brokers that may faucet into every software and information supply with out writing any code. They will leverage MCP to connect 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 just don’t perceive. To me, that is considered one of many value-add use instances of MCP.

Overview of MCP – Structure and Core Elements

MCP has a streamlined structure and there aren’t many shifting elements.

As illustrated in Determine 2 MCP makes use of a consumer/server structure. Let’s outline what the consumer and server parts do.

Determine 2. MCP Elements

Determine 2 reveals an MCP host which is an AI software resembling an AI agent, IDE, coding assistant, and so on..

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 software capabilities.

The MCP host makes use of the language-specific MCP SDK for consumer connections (instance: MCP Python SDK) to determine 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 purchasers are full functions or AI brokers with the MCP consumer SDK performance natively in-built. You possibly can see an instance listing right here: https://modelcontextprotocol.io/clients

There are quite a few sources of MCP server lists on the Web. Here’s a listing from the MCP undertaking: https://modelcontextprotocol.io/examples. Some MCP consumer suppliers, resembling Cursor, have their very own listing of servers: https://cursor.directory/.

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 purchasers 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 purchasers change 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 (Commonplace Enter/Output) because the transport. Determine 3., illustrates how an MCP-C connects to an area MCP-S for file or DB entry utilizing stdio. The MCP-S sends JSON-RPC messages to its normal 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 incredible check software such because the MCP Inspector you possibly can pair an area 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
Related MCP consumer to backing server transport
Created net app transport
Created net app transport
Arrange MCP proxy
Obtained message for sessionId 697bd02d-5d67-4dfc-85b9-6a12d6a99f45
Obtained message for sessionId 697bd02d-5d67-4dfc-85b9-6a12d6a99f45
Obtained message for sessionId 697bd02d-5d67-4dfc-85b9-6a12d6a99f45
Obtained 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 purchasers for native or distant connections. The 2025-03-26 specification modifications states that MCP is shifting to a extra versatile Streamable HTTP transport. Nevertheless, HTTP+SSE transport can nonetheless be used for backward compatibility. This retains it clear, traceable, and tool-agnostic. Notice: As of the time of scripting this weblog, the brand new Streaming HTTP help shouldn’t be accomplished in every SDK.

Determine 4 illustrates the connection movement for HTTP+SSE situations. 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 learn to setup your individual climate consumer/server combo: https://modelcontextprotocol.io/quickstart/server. Utilizing an analogous setup, you possibly can 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-Kind: software/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 software 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-Kind: software/json

{"methodology":"instruments/name","params":{"title":"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,"end result":{"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 absolutely applied as of the writing of this weblog, I’ll forgo doing a granular clarification of that connection sequence. I advisable that you just learn concerning the proposed Streamable HTTP implementation right here: https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http.

Discovery

When an agent must work together with a software or service, MCP offers a useful resource discovery mechanism that lets MCP purchasers uncover out there sources. The MCP consumer can use direct sources or useful resource templates. You possibly can learn extra concerning the useful resource discovery choices at https://modelcontextprotocol.io/docs/concepts/resources. However, the essential factor to know is that the objective 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 movement for the capabilities discovery.

Determine 5. MCP Discovery Move

Whereas there is no such thing as a MCP server registry that MCP purchasers 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 may be an ever-growing variety of MCP directories and in lots of instances, all of them have the identical or comparable listing of MCP servers. Just a few of the various websites embody:

MCP Useful resource Discovery – Instance

Let’s have a look at an instance of useful resource discovery utilizing direct sources.

I’ve the SQLite MCP Server operating on my native machine. I’m utilizing Claude Desktop as my AI software 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"]
    },

After I use Claude Desktop to software name SQLite and ask for an inventory of server sources, you possibly can see the message change from the MCP consumer to MCP server.

2025-04-09T18:08:37.964Z [sqlite] [info] Message from consumer: {"methodology":"sources/listing","params":{},"jsonrpc":"2.0","id":44}
2025-04-09T18:08:37.965Z [sqlite] [info] Message from server: {"jsonrpc":"2.0","id":44,"end result":{"sources":[{"uri":"memo://insights","name":"Business Insights Memo","description":"A living document of discovered business insights","mimeType":"text/plain"}]}}

Per the MCP specification you possibly can see the tactic utilized by the MCP consumer is sources/listing and the MCP server responds utilizing the direct sources format:

{
  uri: string;           // Distinctive identifier for the useful resource
  title: string;          // Human-readable title
  description?: string;  // Non-obligatory description
  mimeType?: string;     // Non-obligatory MIME kind
}

Conclusion

MCP is off to a robust begin, particularly for DevOps groups experimenting with AI-driven automation.

On the similar 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 may be much more introductory content material that I may cowl, however I believe this lays a basis for the remainder of the weblog sequence. For the rest of the blogs it is necessary so that you can know:

MCP is right for:

Brokers want to connect with a number of information sources and providers in a typical method
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 (at the least immediately)?

MCP shouldn’t be an agent-to-agent framework
MCP shouldn’t be used for the creation, deployment, lifecycle administration, and safety of brokers or instruments
MCP shouldn’t be an LLM
MCP shouldn’t be an information supply
MCP doesn’t dynamically uncover instruments and providers the MCP server will signify

We additionally discovered how MCP purchasers and servers work together with each other and over which kinds of protocol and messaging codecs.

Let’s cease there and choose again up within the subsequent weblog on MCP for DevOps: Use Instances

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 sequence

MCP for DevOps: Use Instances

✅ AI Brokers Triggering DevOps Instruments Use MCP to work together with present DevOps scripts, APIs, or providers in a typical format an AI agent can devour.

✅ Infrastructure-Conscious LLMs Let your AI apps ask structured questions like “What kubernetes providers are operating in namespace default?” or “Create a brand new database desk”—with dwell solutions from methods through MCP servers.

✅ Safe Instrument Invocation through AI expose choose CLI instruments or automation workflows via an MCP server interface, permitting AI brokers to work together with them beneath managed situations resembling utilizing a Docker scout MCP to scan photos.

See you on the subsequent submit!