Grafana Labs has released the gcx CLI and the Grafana MCP server to general availability. These tools are designed to integrate live observability data directly into AI coding agent workflows. The announcement was made at GrafanaCon 2026.
The new tools address a challenge in agentic coding, where AI agents can generate code quickly, but developers may lack a full understanding of its operational implications. By allowing agents to query metrics, logs, traces, SLOs, and Synthetic Monitoring results, Grafana aims to provide an evidence-based check on agent output, supplementing traditional code reviews.
The Grafana MCP server offers a fixed set of tools for common use cases and is available self-hosted or via a hosted endpoint for Grafana Cloud. The gcx CLI provides a more flexible option for agents to create custom workflows, compatible with Grafana Cloud, self-hosted OSS, and Enterprise instances. Grafana Labs also provides an installable skill bundle for gcx and Claude Code plugins for the MCP server and a Grafana Assistant guidance layer.
In practice, these tools allow an AI agent to ground implementation decisions in observed system behavior rather than relying solely on its training data. For example, an agent adding a new payment provider can check current RED metrics to determine existing latency, then use this data to set mocked latency for tests and estimate request rates for the new handler.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Grafana Labs announced the general availability of its gcx CLI and Grafana MCP server, tools designed to allow AI coding agents to query live observability data during development. These tools enable agents to access metrics, logs, traces, and other data from Grafana Cloud or self-hosted stacks, addressing the challenge of agents generating code without full developer understanding of its operational impact.