Loading video player...
AI agents are fundamentally changing infrastructure traffic β and traditional load balancers are flying blind. In this demo, we show how to gain deep, real-time visibility into AI/MCP traffic natively using F5 NGINX and OpenTelemetry β with zero backend code changes. Using NGINX JavaScript (NJS) at the proxy layer, we parse JSON streams in real time to extract tool names, client identities, and target MCP servers. Combined with OpenTelemetry and the golden signals (latency, throughput, error rates), you get a comprehensive observability layer for agentic AI infrastructure β exportable to any OTel-compatible backend. π Get the code and try it yourself: [Ihttps://github.com/nginx/nginx-mcp-js/tree/main] π MCP Blog: [https://blog.nginx.org/blog/introducing-agentic-observability-in-nginx-real-time-mcp-traffic-monitoring] Timestamps: 0:00 β Introduction & the AI traffic problem 0:22 β Why AI agents are unpredictable (fan-out behavior) 0:46 β Three critical blind spots: delivery, UX, and observability 1:36 β The NGINX solution: native Layer 7 MCP inspection 2:07 β How it works: NJS parsing + OpenTelemetry golden signals 2:51 β Demo walkthrough: installation & NGINX config 3:12 β Extracting MCP metadata and mapping to OTel spans 3:53 β Running the load generator to simulate AI traffic 4:00 β Grafana dashboard overview 4:19 β Troubleshooting: isolating slow tools 4:46 β Identifying rogue AI clients by identity 5:05 β Monitoring backend MCP server health 5:32 β Wrap-up and next steps Notes: - Contributed by: Akash Ananthanarayanan - Related Article: None β¬οΈβ¬οΈ JOIN THE COMMUNITY! β¬οΈβ¬οΈβ¬οΈ DevCentral is an online community of technical peers dedicated to learning, exchanging ideas, and solving problemsβtogether. Find all our platform links β¬οΈ and follow our Community Evangelists! π β‘οΈ DEVCENTRAL: https://community.f5.com β‘οΈ YOUTUBE: https://youtube.com/devcentral β‘οΈ LINKEDIN: https://www.linkedin.com/showcase/f5-devcentral/ β‘οΈ X: https://x.com/devcentral Your Community Evangelists: π Jason Rahm: https://www.linkedin.com/in/jrahm/ | https://x.com/jasonrahm π Buu Lam: https://www.linkedin.com/in/buulam/ | https://x.com/buulam π Aubrey King: https://www.linkedin.com/in/aubreyking | https://x.com/aubreykingf5 π Chase Abbott: https://www.linkedin.com/in/chaseabbott1