grafana-operations

Query Grafana data sources, dashboards, and alert rules via MCP.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/matt-metivier/zk-hub --skill grafana-operations
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grafana-operations
Source: https://github.com/matt-metivier/zk-hub/tree/main/skills/agent/machines/tp/grafana
Command: npx skills add https://github.com/matt-metivier/zk-hub --skill grafana-operations

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Grafana-based observability configurations are frequently difficult to validate during code reviews. This Skill enables querying Grafana data sources, dashboards, and alert rules through a central MCP server to ensure PRs and deployments reflect correct metrics and alerts.

Core Features & Use Cases

  • Query Grafana through the MCP server to validate data source connections, dashboards existence, and alert rules.
  • Verify Prometheus, Loki, and Tempo integrations across Grafana deployments; review dashboard queries and alert thresholds.
  • Use during reviews to quickly confirm that observability configurations align with expected metrics and alerts.

Quick Start

Query Grafana dashboards and rules via the MCP workflow to surface results for review.

Frequently Asked Questions about grafana-operations

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I validate Grafana dashboards and alert rules during a code review?

You can query Grafana data sources, dashboards, and alert rules through an MCP server to verify pull requests reflect correct metrics and alert configurations.

Can I verify Prometheus, Loki, and Tempo integrations across multiple Grafana deployments?

Yes, you can query the MCP server to verify Prometheus, Loki, and Tempo integrations across Grafana deployments and review dashboard queries alongside alert thresholds.

Do I need an MCP server to query Grafana data sources and alert rules?

Yes, querying Grafana data sources and alert rules requires MCP server access along with proper Grafana token rotation handling.

What happens if the MCP path is unavailable when validating Grafana observability?

If the MCP path is unavailable when validating Grafana observability, the system falls back to manual verification to review configurations.

What is the best way to review horizontal pod autoscaler metrics in Grafana?

The best way to review HPA metrics in Grafana is using MCP-backed queries to surface dashboards and alert rules for validation during code reviews.