Operations | Monitoring | ITSM | DevOps | Cloud

If you’ve been following my public journey with LLMs this year, it probably won’t surprise you to learn that this blog post is an announcement about the general availability of Honeycomb’s hosted MCP server. I want to share a few updates about what’s new in the GA release, discuss some interesting learnings from building it, and share examples of how we’re using MCP internally. First: if you're still in the dark about MCP and AI agents, go read the earlier blogs I linked.

Retail is no longer defined by the checkout counter or button. What used to end with a purchase has expanded into an always-on ecosystem of engagement, media, and service. Every interaction, from browsing to post-purchase, now carries both experience value and monetization potential. This shift has made Retail Media Networks (RMNs) the fastest-growing profit center for retailers, but their scale and complexity demand more than human-led operations or rule-based automation.

At this year’s.conf25, we introduced an exciting new chapter in observability at Splunk — one that is unified, AI-powered, and agentic — to ensure ITOps and engineering teams are digitally resilient in the AI era.

Organizations are under immense pressure to do more with less – streamline operations, reduce costs, all whilst improving both the outcomes of the business and their employees. For IT and end-user computing (EUC) professionals, this challenge is especially prevalent. Systems are becoming increasingly complex, the digital employee experience is now directly tied to customer satisfaction, and the role of technology teams extends much further than solely keeping the lights on.