New Relic introduces support for the Model Context Protocol (MCP) within its comprehensive AI Monitoring solution, fully integrated with New Relic’s best-in-class Application Performance Monitoring (APM). It enables developers building agents that use MCP and the teams providing MCP services to access insights that help pinpoint and resolve any issues with AI applications.
“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 New Relic chief technology officer Siva Padisetty.
“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,” he added.
Capabilities
New Relic’s support for MCP is designed to empower agent developers and MCP providers with a range of capabilities, aiming to give them the control they need to deliver high-quality AI applications.
- Instant MCP tracing visibility: Users can automatically uncover specific usage and patterns of the entire lifecycle of an MCP request, including invoked tools, call sequences, and execution durations with clear waterfall diagrams.
- Proactive MCP optimisation: It enables quick analysisof tools agents select for specific prompts, evaluates tool choices and effectiveness, and tracks usage patterns, latency, errors, and performance to optimise MCP services and demonstrate value.
- Intelligent AI monitoring context: It claims to seamlessly correlate MCP performance with the entire application ecosystem – including databases, microservices, and queues – eliminating the need for screen-swivelling between monitoring tools.
