Grafana's gcx and MCP Server Reach GA for Telemetry-Driven Agent Development
Grafana Labs has announced general availability for two tools that let AI coding agents query live observability data during development: the gcx CLI and the Grafana MCP server. Both allow agents to pull metrics, logs, traces, SLOs, and Synthetic Monitoring results from Grafana Cloud or a self-hosted stack By Claudio Masolo
Grafana Labs has announced the general availability of two new tools designed to enhance telemetry-driven agent development. The gcx CLI and Grafana MCP server integrate with Grafana Cloud or self-hosted stacks, allowing AI coding agents to access live observability data during the development process. This integration aims to improve the alignment between the speed of code generation and engineers' understanding of the code's impact.
These tools address the challenge of developers relying too heavily on code reviews and LGTM approvals, which can create a false sense of confidence in the code's correctness. Grafana Labs positions its solution as providing an additional, evidence-based check on agent output, rather than solely relying on code review. The gcx CLI is a flexible choice, enabling agents to create custom workflows for common use cases, while the Grafana MCP server offers more opinionated tools for managing these workflows.
Both tools provide a way for agents to ground implementation decisions in observed system behavior, rather than assumptions from training data. This integration allows agents to read and modify existing dashboards, trace dashboard queries to the code that generates the telemetry, and push updated dashboard definitions back into Grafana or source control.
Written by urgent.news from InfoQ's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.