Grafana MCP
Query dashboards, metrics, and alerts in Grafana from an AI agent
Last verified: August 9, 2026
How to Install Grafana MCP
$docker run -e GRAFANA_URL -e GRAFANA_API_KEY mcp/grafanaRequires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.
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.
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
- Core MCP server
- Community support
- Works with any MCP client
- Everything in Free
- Higher usage limits
- Priority support
- Everything in Pro
- SLA & SSO
- Dedicated support
Tier details are indicative — visit the Grafana MCP website for current pricing.
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
Screenshots
Screenshots coming soon —
Submit yours →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.