▌BestMCPTools.org
Grafana MCP logo

Grafana MCP

Query dashboards, metrics, and alerts in Grafana from an AI agent

Developer ToolsFreeClaudeCursorVS CodeModerate
Visit Tool3,504 stars

Last verified: August 9, 2026

Own Grafana MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

Active
Last code update: September 28, 2026License: Apache-2.0Checked September 28, 2026

How to Install Grafana MCP

$docker run -e GRAFANA_URL -e GRAFANA_API_KEY mcp/grafana

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "grafana-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-e",
        "GRAFANA_URL",
        "-e",
        "GRAFANA_API_KEY",
        "mcp/grafana"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "grafana-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-e",
        "GRAFANA_URL",
        "-e",
        "GRAFANA_API_KEY",
        "mcp/grafana"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "grafana-mcp": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-e",
        "GRAFANA_URL",
        "-e",
        "GRAFANA_API_KEY",
        "mcp/grafana"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add grafana-mcp -- docker run -e GRAFANA_URL -e GRAFANA_API_KEY mcp/grafana

Add any API keys or environment variables the server's README lists.

About Grafana MCP

The official Grafana MCP server exposes dashboards, Prometheus and Loki queries, incidents, and alert rules to AI assistants. It lets agents investigate observability data and pull metrics or logs without leaving the chat. If your telemetry lives in a hosted platform instead, see the Datadog MCP setup or connect Dynatrace to Claude.

Grafana MCP is a Developer Tools MCP server designed for professional engineers and engineering teams. It enables wiring AI assistants into the inner loop of writing and shipping code by exposing Git, package, build, and CLI operations as MCP tools. Key capabilities include git and github operations (status, blame, prs), package and dependency inspection, build and test runner integration, and structured tool calls that work cleanly inside an LLM context. It integrates with Git, GitHub, GitLab, npm, pnpm, Docker, and common build systems, and is best suited for professional engineers and engineering teams who need reviewing diffs and opening prs from chat.

Key Features

  • Observability
  • Monitoring
  • Metrics
  • Logs
  • DevOps

Pricing

Free: from Free (open source)

Pros & Cons

Pros

  • Acts more like a pair programmer with real tools
  • Tight scoping (one repo, dry-run) limits blast radius
  • Keeps flow inside the editor

Cons

  • Write operations require explicit guardrails
  • Quality of output depends on repo hygiene
  • Larger monorepos may need extra filtering

Best For

  • Reviewing diffs and opening PRs from chat
  • Triaging CI failures
  • Scaffolding new packages or modules
  • Repo-wide refactors with verification

Our Take on Grafana MCP

The go-to server for observability workflows. Open source and maintained by Grafana Labs, it turns your dashboards and logs into something an agent can actually query.

Frequently Asked Questions

Tags

#Developer Tools#Observability#Monitoring#Metrics#Logs#DevOps