Back to Skills Marketplace
Skill pack

Grafana Official MCP

Verified listing for Grafana's MCP server for querying metrics and logs, searching dashboards, managing alerts, and supporting incident workflows.

Verified v0.1.0 1 skill tools By Grafana Labs grafanaobservabilitylogsmetricsalertsincidentsofficialmcpdevops
Publisher docsSourceHosted archive

How to use it

  1. Open Kendr Desktop.
  2. Go to Skills, then Marketplace.
  3. Search for Grafana Official MCP or grafana-official-mcp.
  4. Install the pack, then enable the pack or individual skills you want available in agentic mode.

Kendr Desktop compares the installed version with the hosted catalog version and offers an update when this pack changes.

Install source

Use this hosted archive when installing or updating the pack from Kendr Desktop.

https://kendr.org/api/skills/packs/grafana-official-mcp/archive

Grafana Official MCP

Use Grafana's MCP server for metrics, logs, dashboards, alerts, incidents, OnCall, and production observability workflows.

Grafana Official MCP

Use this skill when the user asks about Grafana dashboards, Prometheus metrics, Loki logs, alert rules, incidents, OnCall, Sift investigations, or production observability.

Setup:

  • Install uv so Kendr can run uvx mcp-grafana.
  • Set GRAFANA_URL in MCP settings when the Grafana instance is not http://localhost:3000.
  • Set GRAFANA_SERVICE_ACCOUNT_TOKEN with the minimum Grafana permissions required for the task.
  • Use a read-focused service account for production diagnostics.

Workflow:

  • Start with read-only dashboard, datasource, metric, log, alert, and incident inspection.
  • Correlate Grafana findings with GitHub deploys, Docker runtime state, cloud resources, or Slack incident context when those packs are installed.
  • Treat alert rule changes, dashboard writes, incident updates, OnCall actions, and datasource changes as side-effecting operations.
  • Use Kendr approval before every side-effecting Grafana action.
  • Do not print service account tokens, datasource credentials, or secret query results.