Loading video player...
AI powered observability. In this DevOps
project, we will be using Honeycomb MCP
server to debug faster than ever.
Honeycomb is one of the most popular
observability tool. And with its MCP
server, you can now understand what went
wrong and how to troubleshoot it without
wasting time digging through logs or
dashboards. You can now ask your
observability questions right in the ID.
For example, what service is slow? Where
is the bottleneck or what changed before
the error started? and Honeycom MCP will
give you instant AI powered answers. To
start using Honeycom MCP server, you
need to create your Honeycom account. Go
to the MCP section and add the MCP
server in any of your favorite IDs.
Could be VS Code, Cursor, Claude,
Windsurf, etc. And for step-by-step
setup or Honeycomb MCP demo, check out
the complete observability project on my
channel and start using Honeycomb MCP
server today. Subscribe.
devops monitoring project | AI Observability | ai telemetry | ai observability demo | mcp ai | observability mcp | gen ai observability | observability ai agent | Ai observability tool In this devops project we look at honeycomb MCP server to debug distributed microservices app, we deploy opentelemetry demo app on kubernetes cluster using helm and setup observability using honeycomb mcp server in vs code What is Honeycomb.io? Honeycomb.io is a modern observability platform designed to help teams understand, debug, and improve distributed systems. It allows you to explore high-cardinality and high-dimensional data, which means you can slice and filter your telemetry in almost any way you want to find the exact cause of performance issues. Honeycomb is used to answer questions such as why a request is slow, what changed after a deployment, or which service is responsible for a spike in errors or latency. It supports fast, interactive querying, distributed tracing, and features like BubbleUp for automatically identifying outliers. Honeycomb is built for environments that use microservices, serverless systems, containers, and dynamic cloud infrastructure. https://www.honeycomb.io/ What is Opentelemetry? OpenTelemetry is an open-source framework and standard for collecting telemetry from applications and infrastructure. Telemetry includes traces, metrics, and logs. OpenTelemetry provides language SDKs, auto-instrumentation, a collector component, and a common protocol (OTLP) to send telemetry to backends like Honeycomb, Datadog, Jaeger, Amazon X-Ray, and others. It solves the problem of vendor lock-in by giving developers one unified way to instrument services. In a microservices environment, OpenTelemetry allows you to capture the full path of a request across services, measure performance, detect bottlenecks, and export all this data to an observability platform. what is honeycomb MCP Server? The Honeycomb MCP Server is an integration that connects Honeycomb with AI agents that support the Model Context Protocol (MCP), such as those integrated into Visual Studio Code. MCP allows external tools to be accessed directly by an AI model. With the Honeycomb MCP Server installed, you can ask your AI assistant observability-related questions inside your IDE. The AI can fetch real data from Honeycomb and help you investigate problems. For example, you can ask it to show slow endpoints, identify which services have the highest latency, run BubbleUp analysis, or inspect traces from a dataset such as the OpenTelemetry demo application. The MCP server essentially turns your AI assistant into an observability companion that can query Honeycomb, analyze telemetry, and assist in debugging distributed systems. https://docs.honeycomb.io/integrations/mcp/ keywords: ai observability llm ai observability snowflake observability zero to hero observability vs monitoring observability application performance monitoring distributed tracing in microservices ai in observability agentic ai observability ai model observability ai and llm observability ai observability with dynatrace aiobservability mcp observability deep observability future of observability application observability ai operations digital resilience with ai ai ops ai enabled observability genai observability autonomous observability self healing observability real time observability intelligent monitoring ai powered monitoring ai assisted debugging next generation observability context aware observability adaptive observability predictive observability ai driven telemetry intelligent telemetry automated root cause analysis ai in devops ai powered sre llm powered devops ai driven monitoring telemetry intelligence full stack observability with ai modern observability practices cloud native observability microservices observability platform engineering observability ai enhanced tracing smart incident response automated incident analysis observability with generative ai ai based performance analysis