Grafana MCP

Connects an agent to a Grafana instance so it can list dashboards, run datasource queries, and inspect alert rules. The value is in incident work: an agent that can pull the same metrics you…

Official stdio Verified 2026-11-09 grafanaobservabilitymetrics

Use it for

Querying dashboards, Prometheus metrics, and alert rules from the terminal agent

Skip it if

Cluster-wide admin tokens; dashboards and datasources should be read-only

What it is

Connects an agent to a Grafana instance so it can list dashboards, run datasource queries, and inspect alert rules. The value is in incident work: an agent that can pull the same metrics you would open in a browser tab can correlate a deploy with a latency change. Give it a viewer-level token.

Install

Terminal
go run github.com/grafana/mcp-grafana@latest

Client configuration

Paste this into your MCP client config, then restart the client.

MCP client config (JSON)
{
  "mcpServers": {
    "avbbc": {
      "command": "npx",
      "args": ["-y", "go run github.com/grafana/mcp-grafana@latest"]
    }
  }
}

Overlapping servers

All servers
  • 01
    SentryOfficial

    Pulls issues, stack traces, and event context into the agent so it can triage production errors with the actual payload in front of it. Remote-hosted, which means no…

    #monitoring#errors#observability
    TypeScripthttp
  • 02
    Datadog MCPCommunity

    Queries the Datadog API for metrics, monitors, dashboards, and incident data. On an incident this turns 'something is slow' into an actual series with a timestamp. C…

    #monitoring#observability#incidents
    TypeScriptstdio