Operations | Monitoring | ITSM | DevOps | Cloud

AI code assistants transformed how software is written. They did not transform how it fails. Today, we’re announcing a new MCP integration between Lightrun and Kiro. Kiro now gains live runtime visibility through the Lightrun MCP, grounding AI-assisted development in how code actually behaves at runtime. Kiro, the AI coding assistant from the teams at AWS, is built for velocity and intuition. It helps teams move from specification to production faster by turning intent into working code.

AI coding assistants like Cursor and Claude Code are driving massive productivity gains, yet they have introduced a critical validation gap in the software delivery lifecycle. While these tools excel at generating syntax, they lack visibility into live production environments. This article explains how Runtime Context, the missing nervous system of AI development, secures production by moving from probabilistic guessing to deterministic, live code validation.

AI code generation is fast. Making it reliable requires runtime context. Today, Kiro gains live runtime visibility with the Lightrun MCP. This grounds AI-assisted development in how code actually behaves at runtime. Kiro, the AI coding assistant from the teams at AWS, is built for velocity and intuition. It moves from specification to production with speed and structure, helping teams turn intent into working code. But until now, like every AI coding assistant, Kiro had a major blind spot.

TLDR: Runtime Context is live, execution-level access to a running production system. It lets engineers and AI agents ask precise questions of running code and get answers immediately, without redeploying or interrupting users. This is the new baseline for reliability.

TLDR: AI coding assistants have sped up code delivery, but created a validation gap. Historic telemetry and static analysis cannot predict the behavior of unfamiliar, high-volume code. Lightrun’s Runtime Context MCP closes that gap, allowing AI assistants to verify behavior before it breaks, and resolve issues in real time.

Safe, Direct Access to Runtime Code Across Staging, Pre-prod and Production via MCP Enables Fundamental Step Forward in Autonomous Software Delivery and Reliability for Enterprises NEW YORK, December 10, 2025 – Lightrun, a leader in software reliability, today launched its new Model Context Protocol (MCP) solution, enabling the industry’s first fully integrated Runtime Context for AI coding agents.

When you’re debugging a tricky issue in a distributed system, “what changed?” is often the most important question. You add logs, you capture data, you redeploy, and suddenly your browser is full of open tabs, copied JSON blobs, and screenshots of log lines. Comparing behavior between two requests, two users, or two releases turns into a manual, error-prone chore. Lightrun Snapshots were built to fix the data collection side of that story.

Every hour developers spend troubleshooting is an hour they’re not building features, innovating, or delivering value to customers. Yet in most organizations, issue management and debugging remains one of the biggest drains on productivity and release velocity. That frustration is exactly what led our founders, themselves developers, to create Lightrun.

(March 18, 2025) — Lightrun is proud to have been named to Fast Company’s prestigious list of the World’s Most Innovative Companies of 2025. This year’s list shines a spotlight on businesses that are shaping industry and culture through their innovations to set new standards and achieve remarkable milestones in all sectors of the economy. Alongside the World’s 50 Most Innovative Companies, Fast Company recognizes 609 organizations across 58 sectors and regions.

Debugging software, whether during development or incident investigation, often begins with a manual and error-prone process. Developers typically scatter logs and snapshots across the codebase, allowing them to trigger multiple times. They then inspect the outputs and sift through the results to identify those relevant to the issue under investigation. Developers tend to group results that stem from the same user request or transaction.