devopsy.kinsta.cloud

Tag: MCP

How Model Context Protocol (MCP) is Fueling the Next Era of Developer Productivity

The landscape of software development is undergoing a profound transformation, driven largely by the rapid advancements in AI. As developers increasingly integrate AI models into applications, a new challenge has emerged: Resource and tool fragmentation. Building sophisticated applications often involves stitching together disparate AI models, diverse tools and various data sources through complex, point-to-point integrations. This approach is not only time-consuming but also inherently unscalable, leading to repeated code modifications for different platforms or contexts.

But what if there was a universal connector, a standard protocol that could streamline this complexity, much like a USB-C port simplifies connecting various devices to a laptop? This is precisely the problem Model Context Protocol (MCP) aims to solve.

What is MCP and Why Does it Matter?

MCP is an open standard protocol designed to standardize how AI models understand and effectively use the tools and resources available to them. Think of it as that universal connector for your applications. Instead of building custom integrations for every new tool or platform, developers can create a single “MCP server” for a tool, making it instantly accessible across any client or system that supports the protocol. This paradigm shift means you can “build once and then start using it” across a multitude of AI-powered applications.

The core benefit lies in standardizing the communication between the tool and the AI model once and then being able to reuse it. Imagine a scenario where a developer builds a tool for working with AI using Python. If the same tool is needed in a collaboration software or an integrated development environment, this would require significant code changes. With MCP, the standardized approach eliminates this repetitive work, allowing for seamless integration and reuse of tools.

Revolutionizing the Developer Experience

MCP promises to profoundly impact the daily lives of developers by transforming how they interact with their toolchains. Currently, many agentic IDEs often “guess” how to perform actions, leading to inefficient API calls and slower iteration cycles. MCP addresses this by providing agents with a trusted set of tools that deliver consistent and reliable outcomes. This means agents can achieve desired results faster, with fewer wasted resources, significantly boosting productivity and reliability.

A key concept emerging from this shift is “vibe coding.” Instead of memorizing complex command-line interface (CLI) syntax or constantly referring to documentation, developers can express their intentions in natural language to an AI agent. The MCP server then interprets this natural language, identifies the correct tools, and executes the appropriate commands. This iterative, conversational approach not only accelerates development but also mitigates issues arising from outdated training data in AI models, as the MCP server ensures the agent uses the most current and correct commands. Moreover, sophisticated MCP tools can provide corrective instructions back to the agent if a mistake occurs, further optimizing the development loop and reducing unnecessary API calls.

Building a Secure and Interoperable AI Ecosystem

The power of MCP extends beyond individual developer productivity to foster a robust and secure AI ecosystem. The concept of certified or pre-validated MCP servers will play a crucial role, making it easier for organizations to discover and integrate trusted tools. Alongside these vetted options, the flexibility to register private or external MCP servers ensures that proprietary tools and internal logic can also be exposed securely.

For example, AWS, Box, Cisco, Google Cloud, IBM, Notion, PayPal, Stripe, Teradata, WRITER and more are planning to offer plug-and-play MCP servers in AgentExchange, Salesforce’s AI agent marketplace for Agentforce. Organizations can connect Agentforce, Salesforce’s digital labor platform, to PayPal’s MCP server, allowing them to benefit from a full range of agentic commerce capabilities.

A critical aspect of enterprise adoption is security and governance. Organizations need assurance that their data and policies are upheld when AI agents interact with external tools. This can be addressed through centralized “agent gateways” where MCP servers can be registered. These gateways enable administrators to allowlist specific tools, ensuring only approved functionalities are exposed to agents. Additionally, the ability to wrap custom MCP actions with business policies provides essential guardrails, maintaining control over how these external tools operate within an organization’s context.

Concerns about data security, particularly regarding the use of proprietary data for training external large language models (LLMs), are paramount. By leveraging trusted, managed, or “platform-hosted” MCP servers, organizations can ensure that their data remains within secure boundaries, mitigating the risks associated with general-purpose LLM. These secure environments prioritize trust, offering managed and controlled experiences for exposing organizational logic and assets over MCP.

The Path Forward

MCP marks a significant step toward a more interconnected, efficient, and secure future for AI-powered development. By standardizing the interaction between AI agents and tools, it addresses critical fragmentation issues, enhances developer productivity through intuitive “vibe coding” experiences, and provides the necessary governance for enterprise-grade AI adoption.

As the AI landscape continues to evolve rapidly, open standards like MCP will be instrumental in unlocking the full potential of AI across all industries.

October 1, 2025
env zero Revamps Infrastructure Automation Platform for AI Era

env zero (formerly env0) today revealed it has revamped its infrastructure automation platform to add artificial intelligence (AI) capabilities, including beginning next month a Static Code Analyzer Agent to identify and troubleshoot issues.

Chris Graham, chief marketing officer for env zero, said this iteration of the company’s Cloud Governance Platform will provide a control plane for automating and governing infrastructure-as-code that now takes advantage of AI to better connect repositories and cloud computing platforms using a Model Context Protocol (MCP) server. Originally developed by Anthropic, MCP is emerging as a de facto standard for exposing data to AI applications and agents.

The core capability is also making it possible to build a Static Code Analyzer Agent that detects who is accessing services, the level of compliance, data protection, security and protection of secrets that is being achieved and maintained, which can then be remediated via a pull request that is generated via a single click using the Cloud Governance Platform.

Compatible with Terraform, OpenTofu, Pulumi, CloudFormation, Terragrunt and Kubernetes tools, the Cloud Governance Platform is now making it simpler for AI agents to be used to programmatically provision cloud infrastructure in a way that enables policies to be enforced as code, said Graham.

The ultimate goal is to dramatically increase the pace at which IT infrastructure can be safely provisioned using the context that can be uniquely provided by the Cloud Governance Platform developed by env zero without requiring DevOps teams to master a completely separate user interface, he added.

It’s not clear to what degree organizations are embracing IT infrastructure automation platforms, but the rise of AI agents might soon force the issue. AI agents, while improving productivity, will need a set of guardrails to be in place that prevent them from exceeding the scope of the task that they have been assigned. Otherwise, it becomes probable that sensitive data will be exposed to either an AI agent or the application development team employing them in a way that runs afoul of any number of compliance requirements.

Ultimately, AI agents invoking MCP servers should also reduce the number of scripts and application programming interfaces (APIs) that DevOps teams currently need to support. As the overall complexity of DevOps workflows is reduced, it then becomes feasible to provision more infrastructure at scale at a time when AI is also dramatically improving the pace at which applications are being developed.

Each DevOps team will need to determine to what degree to rely on AI agents to automate tasks, but, for now at least, those teams would be well advised to review any code created by an AI agent. In the meantime, DevOps engineers would be well-advised to start identifying more tasks than can be potentially performed by AI agents as part of a larger effort to reduce the total amount of manual toil that, in addition to burning out teams, also creates more bottlenecks that slow down the pace of application development more than anyone cares to admit.

September 30, 2025
Building End-to-End Trust in the Software Supply Chain

At swampUP 2025, JFrog’s Guy Levi, head of the architects team, highlights some of the technologies shaping the company’s next chapter. Levi’s role centers on exploring advanced technologies “beyond the horizon,” but he emphasized that swampUP isn’t about future promises — it’s about showing what’s available today.

One of the highlights Levi pointed to was AppTrust, JFrog’s initiative to establish end-to-end trust across the software supply chain. By unifying governance, risk, and compliance capabilities into a single framework, AppTrust is designed to give enterprises more confidence that applications are secure and reliable from development through deployment. The goal is to tie disparate security and verification processes into one cohesive approach that simplifies how organizations enforce trust at scale.

Another major focus was JFrog Fly, which Levi described as a breakthrough in supporting AI-era DevOps. Fly provides an “agentic repository” that integrates with Anthropic’s Model Context Protocol (MCP) to enable AI agents to securely interact with APIs and development pipelines. With AI-generated code and autonomous agents becoming part of daily workflows, Fly aims to ensure those components can be governed, tracked, and optimized just like traditional software artifacts.

Together, these initiatives underscore JFrog’s push to position itself as the system of record for modern DevOps and AI-driven development. AppTrust tackles the governance side, while Fly addresses how AI agents and automation will reshape pipelines.

For Levi, the key message was that the industry can’t afford to wait for “next year” to solve these challenges. AI and security pressures are already here, and JFrog is working to deliver the tools teams need now to navigate them.

September 19, 2025
Honeycomb Adds Ability to Orchestrate Multiple AI Agents to Observability Platform

Honeycomb has added a Canvas framework for managing and orchestrating multiple artificial intelligence (AI) agents as they observe and query massive amounts of telemetry data.

Morgante Pell, technical lead manager for engineering at Honeycomb, said Canvas is the latest extension to a series of Honeycomb Intelligence initiatives that, for example, provide access to an AI agent that can convert natural language into queries based on the syntax Honeycomb created to query data. There is also now a Model Context Protocol (MCP) server that provides third-party agents and coding tools with access to observability data.

These capabilities will enable DevOps teams to both more easily interrogate terabytes of telemetry data and be alerted any time there is anomalous behavior that might adversely impact application performance and availability.

Honeycomb also plans to add additional AI agents that are capable of completing tasks that run in the background later this year, he said. That will make it possible for an AI agent to, for example, autonomously observe application behavior and surface remediation suggestions that might be required, said Pell.

Additionally, Honeycomb is working toward integrating the codebase analysis tools it gained earlier this year via the acquisition of Grit into the Honeycomb Intelligence framework.

The overall goal is to make observability data more accessible to not just DevOps engineers but also additional members of the IT teams that no longer need to know how to craft a Honeycomb query, noted Pell.

Arguably, one of the reasons that observability platforms are not more widely employed is that many IT professionals simply lack the expertise required to create the query needed to analyze data in the first place. In effect, AI is democratizing access to observability platforms.

Less clear is to what degree AI may encourage more IT teams to rationalize legacy IT monitoring platforms that are designed to track a set of pre-defined metrics. While observability platforms are today used primarily to troubleshoot application environments, they can also be used to track events. As AI tools become more deeply embedded within the observability platform, it should become easier to use a single platform at a lower total cost to both monitor metrics and analyze logs and traces.

Ultimately, each IT organization will need to decide to what degree it may empower AI agents to autonomously act on guidance surfaced by an observability platform, but in most instances a DevOps engineer is going to want to review them before allowing them to be implemented in a production environment. Eventually, however, platforms will automatically handle issues with relatively low risk of impacting an application, while routing issues that could impact customers being sent to an on-call system to ensure they get immediate attention from a DevOps professional.

Hopefully, in the age of AI there will soon be a lot less firefighting as more issues are resolved before they can have a catastrophic impact on the application environment. The challenge now will be organizing the small army of AI agents that might be needed to achieve that goal.

September 17, 2025
Sketch Coding and the Rise of MCP in DevOps

At swampUP 2025, JFrog’s Yonatan Arbel reflects on his journey inside the company and how developer DNA continues to shape JFrog’s culture. Arbel, who has spent nearly a decade with JFrog, began as a software engineer before moving into leadership and eventually into a developer relations role. But as he emphasized, “once a developer, always a developer.” He still codes daily, keeping a hands-on perspective that influences how JFrog builds and communicates its platforms.

That commitment to staying close to the keyboard led Arbel to create JFrog’s first experimental MCP (Model Context Protocol) server as an open source project. Uploaded to GitHub almost as a side experiment, the project quickly gained traction — even attracting pull requests from NVIDIA and references from Cisco. For Arbel, it was validation that MCP represents a real turning point in how enterprises will connect APIs, AI models, and DevOps workflows.

He described his process as “sketch coding,” akin to vibe coding, where ideas start as rough AI-assisted prompts before maturing into production-ready tools. That approach mirrors how many developers are now blending AI into their workflows: iterating quickly, validating ideas, and only then investing in hardening code for scale.

Arbel also highlighted the excitement — and occasional sense of magic — that comes from integrating AI into day-to-day development. Whether it’s pulling runtime insights from an IDE or rapidly prototyping new capabilities, the goal remains the same: help developers work smarter while ensuring JFrog’s platforms support security, governance, and scalability across the software supply chain.

The conversation underscored how JFrog continues to bridge its engineering roots with the demands of modern DevOps, proving that innovation often starts with developers who never stop building.

September 12, 2025
JFrog CEO: AI Agents Require Practices Beyond Security, Traceability

NAPA, Calif. — A new persona in software development, artificial intelligence (AI) agents rather than human developers, has made it imperative that foundational platforms incorporate agentic practices alongside security, traceability, and visibility to succeed in the AI era.

“Every foundational platform requires a single system of record,” Ben Haim told the crowd. “If you don’t have that, you don’t have an anchor to build a platform around,” JFrog CEO Shlomi Ben Haim said in the opening keynote at swampUP 2025, the company’s annual conference here.

Speaking to developers and IT professionals, Ben Haim highlighted what he called “AI FOMO,” noting that 40% of CIOs are increasing their budgets because of board-level pressure around AI adoption, according to Gartner. When he asked attendees to raise their hands if they already had AI embedded in their software supply chains, nearly everyone responded affirmatively. “If you don’t, you can leave the room,” he said to laughter.

Ben Haim called JFrog “the system of record for your software supply chain” amid daily attacks on software infrastructure.

To that end, JFrog unleashed a slew of announcements Tuesday. It launched JFrog Fly, a DevOps platform that simplifies AI agent integration for application developers working at scale. Built on Anthropic’s Model Context Protocol (MCP), Fly connects with popular development tools including Cursor, GitHub Copilot, and Claude Code, allowing DevOps teams to centrally manage software components through semantic metadata while optimizing release deployments and integrating with package managers and GitHub repositories.

Yoav Landman, chief technology officer and co-founder at JFrog, addressed the “liquid software” climate in which “latest is king.”

“This has made a handful of questions harder to answer, including what makes up a release? And how do I track it?” asked Landman, who believes one key is a system of record that manages agentic releases.

The company has introduced AI agents that automatically remediate software vulnerabilities by applying real-time policy analytics during code development. Alongside this, JFrog launched its AppTrust platform, which serves as a unified hub for governance, risk management, and compliance (GRC) teams. Supporting this ecosystem, JFrog has established the Evidence Ecosystem through AppTrust partnerships with GitHub, ServiceNow, SonarQube, Akuity, Akto, Coguard, Dagger, Nightvision, Shipyard, and Troj.ai.

Additionally, JFrog overhauled its AI model catalog with a new Secure Model Registry that enables governance policy enforcement and cost tracking across multiple models.

“The pressure and forces from the top and boards has prompted companies to consider how do you use the leverage? And that has put pressure on the bottom for users,” Fred Simon, chief data scientist and co-founder of JFrog, said in an interview.

“But do I see a slowdown in the order of magnitude of speed and complexity? No,” he added.

“No one wants to be left behind and be the Blockbuster of this technology era,” Guy Levi, architects lead at JFrog, said in an interview.

Following his introductory remarks, Ben Haim was joined onstage by several executives whose companies partner with JFrog.

Sonar CEO Tariq Shaukat predicted that while much will change with AI adoption, core principles will remain constant. “It’s never been about how fast developers type on a keyboard,” Shaukat said, advocating a “trust, but verify” approach to AI-generated code. “We’re helping with that verification step as software is being written,” he said.

“Trust, but verify, or ‘Vibe then verify.’ We’re helping with that verification step as software is being written,” Shaukat added.

Rahul Tripathi, who leads ServiceNow’s IT Service Management business, emphasized the tension between speed and security in running large DevOps teams. “Nobody wants to receive a notification that our software was breached,” he said. “It’s about getting IT Ops moving at the speed of DevOps.”

Yet there are two classes of companies, he said — those willing to take risks and those slow-playing AI, he said in an interview late Tuesday.

Justin Boitano, vice president of enterprise AI at NVIDIA, said his company’s approach to scaling AI development, revealing that CEO Jensen Huang had challenged the team to double chip production, which could only be achieved by “infusing AI across our lifecycles.” Boitano noted that performance-optimized models can achieve double or triple token efficiency improvements.

When Ben Haim asked whether AI would replace human developers, Boitano downplayed the concern. “I think that’s over-hyped,” he said. “We see it as improving productivity across the board.”

The discussion underscored the industry’s focus on balancing AI adoption with governance and security concerns as organizations navigate the rapidly evolving technological landscape.

September 9, 2025
Why APIs Alone Won’t Cut It in the AI Era

Kumar Chivukula, co-founder and CEO of Codeglide.ai (a subsidiary of Upsera), explains why the rise of the Model Context Protocol (MCP) is reshaping how enterprises connect APIs to large language models. For years, APIs have served as the backbone of data access, but they were never designed with AI in mind. They lack memory, context, and intent awareness—forcing developers to bolt on brittle glue code every time models change.

Anthropic’s introduction of MCP earlier this year marked a turning point, offering a standardized way to make APIs context-aware and AI-ready. But as Chivukula points out, adopting MCP isn’t just about creating a one-off server. Enterprises run tens of thousands of APIs—many undocumented, outdated, or internally facing—and keeping pace with rapid model changes demands a lifecycle approach. That’s where CodeGlide positions itself: a continuous MCP server platform that automates creation, updates and security scanning at scale.

The comparison to cloud migration is apt. Just as lift-and-shift approaches left organizations with bloated costs, treating MCP as a quick wrapper on existing APIs won’t cut it. Instead, enterprises need a sustainable framework that refactors APIs for AI interaction, enforces security, and manages change continuously. Chivukula highlights integration with GitHub’s vast ecosystem—home to tens of millions of API repositories—as a critical lever to reach both developers and enterprises.

With more than a billion APIs in existence and an emerging AI economy valued in the tens of billions, MCP adoption isn’t optional—it’s inevitable. The question is how organizations will navigate the transition without drowning in complexity. Platforms like CodeGlide hint at one possible path forward.

August 29, 2025
MCP Emerges as a Catalyst for Modern DevOps Processes

Loreli Cadapan, VP of product at CloudBees, discusses how the Model Context Protocol (MCP) developed by Anthropic will provide the foundation for reinventing DevOps workflows.

Cadapan explains that MCP acts as a bridge between large language models and enterprise DevOps environments, functioning as a kind of control plane. It can connect with different CI/CD tools and testing frameworks, pull in real-time data on pipelines and vulnerabilities, and even orchestrate tasks across the software delivery lifecycle. By reducing context switching and integrating with existing developer tools, MCP is designed to improve both productivity and governance.

She compared MCP servers to factory floor managers—directing specialized AI agents that handle specific tasks such as diagnosing build failures or recommending tests. The challenge, she noted, is ensuring those agents are trained on the right data. As with any AI, the quality of output depends heavily on the quality of the inputs and feedback they receive.

Cadapan acknowledged that AI adoption varies across organizations. Some want co-pilot style assistance with humans in the loop, while others are experimenting with allowing agents to fully automate parts of their workflows. Either way, she stressed that guardrails and policies must be in place so that outcomes are reliable, secure, and aligned with enterprise requirements.

Looking ahead, Cadapan sees AI changing not just coding and pipelines but also product management practices, from drafting requirements to validating solutions. As AI-generated code and commits increase, bottlenecks are shifting downstream—from developers to reviewers and pipelines. Her advice for teams is to stay informed, experiment carefully, and validate outputs rather than trusting AI blindly.

The broader message: MCP and AI agents are early steps toward rethinking the entire software delivery lifecycle. As software delivery accelerates and AI-generated code becomes commonplace, the real challenge will be ensuring pipelines, governance, and teams evolve at the same pace. For DevOps practitioners, that means preparing now for a future where AI is embedded in every stage of the lifecycle.

August 21, 2025
Sentry Adds Tool for Monitoring MCP Servers to APM Platform

Sentry today added an ability to monitor Model Context Protocol (MCP) servers to its application performance monitoring (APM) platform.

Originally developed by Anthropic, MCP has emerged as a de facto standard for enabling artificial intelligence (AI) applications to access data that is rapidly being adopted by software development teams.

Cody De Arkland, senior director of developer experience for Sentry, said that as application developers increasingly use AI technologies to build applications, many of them are employing MCP servers to now access the data those applications require. By adding a few lines of code using JavaScript software development kit (SDK), the MCP Server Monitoring tool from Sentry provides DevOps teams with visibility into how well each MCP server they have deployed is functioning to facilitate debugging tasks that might be required, he added.

For example, the MCP Server Monitoring developed by Sentry makes it possible to track traffic load and AI client usage, which tools were getting called the most, which were slow or failing, and which inputs were causing specific issues.

It’s not clear how widely MCP servers may have been deployed by DevOps teams, but they are expected to rapidly proliferate across software engineering workflows. In fact, as more AI applications are built, the need for DevOps teams to troubleshoot MCP servers is only going to increase, noted De Arkland.

In the meantime, DevOps teams should at the very least be spending more time becoming familiar with MCP. MCP is an application-layer protocol, carried by HTTP/S and invoked via an application programming interface (API), but operating at the very top of the application stack. MCP moves business logic — application context, state and intent — between autonomous actors. And unlike a lot of so-called “stateless” protocols, MCP drags state along with it, making context the payload, the product and the target, all at once.

On the plus side, that approach eliminates the need for DevOps teams to set up and maintain ad hoc integrations between each model and each system. MCP provides a scalable method for enabling AI systems to access, process and act upon information coming from any external data source. That capability is especially critical for any autonomous AI agent that organizations expect to deploy. However, it also creates a new set of rich potential targets for cybercriminals that could lead to entire processes and workflows becoming compromised. As such, being able to monitor and observe what is happening within an MCP server will be a crucial DevSecOps requirement.

Ultimately, DevOps workflows will need to be re-engineered to accommodate MCP servers. That task in and of itself is not likely to be especially disruptive. The challenge and the opportunity stem from the fact that MCP servers, in addition to facilitating integration, also provide a focal point for monitoring and observing AI application workflows. As a result, any organization that deploys MCP servers without some ability to monitor and observe them will be losing a significant opportunity to build better AI applications, which over time are only going to become much more complex to build, deploy, secure and manage.

August 14, 2025
AI-Driven Observability: Fast, Context-Rich MCP Servers

Christine Yen—developer-turned-CEO—explains why Honeycomb built an MCP server and why every observability vendor may follow. MCP, short for Model Context Protocol, acts like a concierge for AI agents: It makes a product’s API, telemetry schema and helper tools easily discoverable so large-language models can ask precise questions instead of guessing. Yen sees it as table stakes for letting bots troubleshoot production just as humans do.

Speed is the first requirement. Engineers won’t wait minutes for an LLM to fetch a log slice or distribution graph. Honeycomb’s mantra—fast is a feature—now pays off when an agent fires off dozens of sub-queries during root-cause analysis. Yen jokes that no one wants to brew coffee while a model thinks, so the platform’s near-instant queries translate directly into snappier conversational answers.

Depth of data is the second pillar. Because customers pipe richly labeled events (“checkout_latency_ms”, “user_tier”) instead of fixed dashboards, even off-the-shelf models can map plain-English prompts to meaningful fields. Yen argues this beats the “narrow metric lists” many teams still rely on; a model that understands business context can pinpoint anomalies without endless prompt engineering.

Yen admits she no longer remembers every field in Honeycomb’s own dog-food cluster—but the MCP server does. She expects newcomers to treat agents as default copilots, while power users toggle between raw queries and natural language. The challenge for vendors, she says, is balancing both paths without forcing engineers into one camp.

Yen’s closing advice: start experimenting now, map where your context lives and demand that every tool expose it through open protocols. The future observability stack won’t just collect data; it will serve it—fast and in the right context—to whatever human or agent asks first.

August 4, 2025