New Relic unveils Agentic AI monitoring and MCP server for deep observability

New Relic, the Intelligent Observability company, has announced two breakthrough innovations, Agentic AI Monitoring and the New Relic AI Model Context Protocol (MCP) Server, designed to transform how enterprises observe, optimise, and scale complex AI ecosystems. Together, these capabilities provide end-to-end visibility into agentic AI systems while embedding observability directly within developer workflows.

Agentic AI Monitoring delivers a holistic view of AI agents and their interactions, while the AI MCP Server opens the platform to a growing ecosystem of AI assistants, including GitHub Copilot, ChatGPT, Claude, and Cursor, that can now access detailed New Relic data directly from within their environments.

“The convergence of AI workloads, cloud-native architectures, and real-time data processing has created a perfect storm of complexity,” said Brian Emerson, Chief Product Officer, New Relic. “Our platform uses intelligent automation and unified data correlation to diffuse that complexity so businesses can operate confidently and at scale. These new capabilities empower organisations to adopt AI systems that deliver measurable business value.”

Taming Complexity in the AI Age

As enterprises integrate agentic AI systems into their operations, complexity rises rapidly. Multiple agents often rely on each other’s outputs across different MCP servers, forming interdependent networks where a single error can cascade downstream. New Relic’s latest features address these challenges head-on by making every layer of AI collaboration observable.

The 2025 Observability Forecast reveals that the use of AI monitoring capabilities has grown from 42% in 2024 to 54% in 2025, as organisations respond to rising costs of downtime. High-impact outages now cost a median 2 million USD per hour, underscoring the need for real-time visibility into AI-driven environments.

Agentic AI Monitoring: Deep Visibility Across Multi-Agent Ecosystems

New Relic’s Agentic AI Monitoring provides a granular, unified view of how agents and tools interact across multi-agent workflows. It visualises every agent call, tool invocation, and inter-agent dependency, giving DevOps and engineering teams the ability to detect issues, reduce mean time to resolution (MTTR), and prevent cascading failures.

Key features include:

• Agents Service Map: Visualises inter-agent communication and dependencies.

• AI Inventory: Displays all active agents, tools, latency data, and errors in one view.

• Performance Tracing: Enables fast root cause analysis of errors and slowdowns.

Unlike isolated LLM monitoring tools, New Relic’s approach extends observability across agents, infrastructure, and supporting services, helping teams correlate application performance with AI behaviour.

New Relic AI MCP Server: Extending Observability to AI Agents

The New Relic AI MCP Server unlocks a new level of integration for AI-driven development environments. It allows AI assistants and tools, such as GitHub Copilot or ChatGPT, to query live observability data without leaving their workflow.

This capability bridges a critical gap in AI software delivery, giving engineers direct access to production insights from inside their development environments. By reducing context switching, the AI MCP Server improves uptime, shortens MTTR, and accelerates time-to-market for new releases.

“As enterprises deploy agentic AI to accelerate software delivery, engineers have lacked direct access to observability data,” said Stephen Elliot, Group VP at IDC. “Platforms like New Relic’s MCP Server will fill that gap, creating an intelligent feedback loop that makes both AI systems and observability platforms more adaptive, reliable, and proactive.”

Outlier Detection: Proactive Issue Resolution

Alongside these new releases, New Relic introduced Outlier Detection, a complementary capability that enhances anomaly detection by pinpointing aberrant behaviours and failure patterns. The system not only flags potential issues but also helps teams prioritise remediation before end-user impact occurs, strengthening proactive resilience across complex AI and cloud environments.

Availability

Agentic AI Monitoring, the New Relic AI MCP Server, and Outlier Detection are currently available in limited preview as part of the New Relic Intelligent Observability Platform.

Read More:

How AI-driven cybersecurity is redefining B2B ecosystem?

India to lead in process Intelligence and AI: Sarangadhar Sahani, Celonis

Beyond Make in India: How IMS 2025 is powering the next era of industrial self-reliance

How AI-driven cybersecurity is redefining B2B ecosystem?