New Relic has announced support for the Model Context Protocol (MCP) within its AI Monitoring solution, aiming to give developers and service providers deeper visibility into AI applications. The update is integrated into New Relic’s Application Performance Monitoring (APM) tool, enabling end-to-end observability across AI agents, MCP servers, and backend services.
Greater transparency across AI systems
The MCP protocol has rapidly emerged as a key standard for agentic AI since its release last year. MCP servers act as intermediaries that allow AI agents to interact with various tools and services. However, these servers have often been regarded as opaque, offering limited visibility into tool usage, performance, and error tracking. New Relic’s latest update addresses this gap.
“Since it was released last year, MCP has quickly become the standard protocol for agentic AI. Once again meeting our customers where and how they work, our new MCP integration is a game-changer for anyone building or operating AI systems that rely on this protocol,” said Siva Padisetty, Chief Technology Officer at New Relic.
He added, “We’ve moved beyond siloed LLM monitoring to demystify MCP, connecting insights from AI interactions directly with the performance of the entire application stack for a holistic view. All this is offered as an integral part of our industry leading APM technology.”
New tools for developers and providers
The integration enables automatic tracing of the entire lifecycle of MCP requests, including tool usage, call sequences, and execution durations. Developers and MCP service providers can now analyse how tools are selected and used in response to prompts, as well as track latency, performance, and error rates. Waterfall diagrams and other visual tools support quick diagnosis and optimisation without the need for manual instrumentation.
The new capabilities also allow teams to correlate AI performance with other components in the application stack, such as databases, microservices and queues. This eliminates the need to toggle between different monitoring systems, making it easier to identify issues and optimise AI operations in real time.
Supporting enterprise adoption of AI
New Relic’s AI Monitoring platform is available under a usage-based pricing model, aligning costs with the actual value received rather than by seat count. According to the company’s AI Unwrapped: 2025 AI Impact Report, adoption of its AI Monitoring solution has grown by 30% quarter-over-quarter over the past year.
As AI technologies become more embedded in enterprise systems, businesses are looking for solutions that can ensure reliability, compliance and cost efficiency. The new MCP support is designed to help customers accelerate their AI initiatives by reducing operational overhead and simplifying performance troubleshooting.
New Relic AI Monitoring with MCP support is available now as part of the Python Agent version 10.13.0, with support for more programming languages planned.
