New Relic has unveiled two major innovations, Agentic AI Monitoring and the AI Model Context Protocol (MCP) Server, designed to enhance enterprise observability and support the integration of agentic artificial intelligence into production systems. Together, these capabilities aim to transform complex AI environments into more transparent, manageable systems, enabling teams to deliver reliable software in the AI-driven era.
Agentic AI Monitoring gives organisations complete visibility into interconnected AI agents and tools, allowing them to optimise performance and prevent downtime. Meanwhile, the New Relic AI MCP Server introduces a standardised way for AI assistants, including GitHub Copilot, ChatGPT, Claude, and Cursor, to directly access observability data from New Relic’s platform. This connection embeds real-time insights within engineers’ daily workflows, improving collaboration between AI and human developers.
Brian Emerson, Chief Product Officer at New Relic, said, “The convergence of AI workloads, cloud-native architectures, and real-time data processing has created a perfect storm of complexity. Our platform uses intelligent automation and unified data correlation to diffuse that complexity so you can operate your business confidently and at scale. Our latest innovations further empower enterprises to adopt AI systems that create real business value, rather than cutting into the bottom line.”
Addressing the challenges of agentic AI
As organisations increasingly adopt agentic AI systems, their internal architectures are becoming more complex. These systems often involve multiple agents that depend on one another, drawing information from various MCP servers and shared memory. This interdependence can make it difficult to trace the source of an issue, especially when one agent produces inaccurate data that others rely on.
New Relic’s Agentic AI Monitoring is built to address these challenges. It offers end-to-end observability into every agent and tool call within collaborative AI systems. Users can now see how agents interact, track communication patterns, and access detailed data on performance, latency, and errors. The platform’s AI Inventory view provides a complete overview of all active agents and tools, while the Agents Service Map visualises interactions and allows teams to drill down into specific performance details.
Unlike traditional monitoring tools that only track individual large language models (LLMs), New Relic’s approach connects agent monitoring with infrastructure and service-level observability. This gives engineering and DevOps teams a unified view of the entire AI ecosystem, helping them diagnose issues faster, improve system reliability, and optimise efficiency across the full AI-enabled technology stack.
Expanding access with the AI MCP Server
The new AI MCP Server further enhances collaboration between engineers and AI assistants. It allows agents to access real-time observability data directly from New Relic without requiring users to switch between platforms. This integration helps engineers retrieve deep insights into system performance from within their preferred AI tools, reducing downtime and accelerating incident resolution.
IDC Group Vice President Stephen Elliot commented, “As enterprises deploy agentic AI to accelerate software delivery, engineers have lacked direct access to observability data within their workflows. Observability platforms will need to fill that gap by making observability capabilities available to any MCP-compatible agent. By creating an intelligent feedback loop where AI systems become more observable and reliable, while observability platforms become more intelligent and proactive, the industry can equip enterprises with the confidence needed to innovate at speed.”
Enhancing performance with outlier detection
In addition to these AI-focused releases, New Relic has introduced Outlier Detection, a new feature that complements its existing anomaly detection capabilities. Outlier Detection helps teams identify and analyse unusual behaviours or performance deviations that may indicate potential failures. By flagging these issues early, teams can take proactive measures to prevent them from affecting end-users. The feature not only detects anomalies but also supports faster resolution by prioritising remediation efforts.
Availability
Agentic AI Monitoring, the AI MCP Server, and Outlier Detection are currently available in limited preview through the New Relic Intelligent Observability Platform.
