Grafana is a Monitoring MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent dashboard and observability platform. Install in 1 minute with mcpizy install grafana.
Monitoring
Dashboard and observability platform
Official homepagemcpizy install grafananpx -y mcp-grafanalist_dashboardsList Grafana dashboards
Inputs
querystringoptionalget_dashboardGet a dashboard by UID
Inputs
uidstringrequiredquery_prometheusRun a PromQL query
Inputs
querystringrequiredstartstringoptionalendstringoptionalquery_lokiQuery logs via LogQL
Inputs
querystringrequiredlist_datasourcesList configured datasources
list_alertsList alert rules
Works identically across clients. Only the config file path differs.
~/.claude.json{
"mcpServers": {
"grafana": {
"command": "uvx",
"args": [
"mcp-grafana"
],
"env": {
"GRAFANA_URL": "https://grafana.example.com",
"GRAFANA_API_KEY": "glsa_..."
}
}
}
}.cursor/mcp.json{
"mcpServers": {
"grafana": {
"command": "uvx",
"args": [
"mcp-grafana"
],
"env": {
"GRAFANA_URL": "https://grafana.example.com",
"GRAFANA_API_KEY": "glsa_..."
}
}
}
}~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"grafana": {
"command": "uvx",
"args": [
"mcp-grafana"
],
"env": {
"GRAFANA_URL": "https://grafana.example.com",
"GRAFANA_API_KEY": "glsa_..."
}
}
}
}Paste any of these prompts into Claude Code, Cursor or another MCP-compatible client.
“What's the current CPU usage of my production nodes? Use PromQL.”
Uses: query_prometheus
“Show me 5xx errors from my API in the last 30 minutes via Loki”
Uses: query_loki
“List dashboards tagged `production`”
Uses: list_dashboards
Access OpenTelemetry traces and metrics via Pydantic Logfire. Debug production issues fast.
Crash reporting and real user monitoring data. Track errors, performance, and user sessions.
Real-time production context — logs, metrics, traces. SRE intelligence for incident response.
Query metrics and alerts
If Grafana doesn't fit your stack, these Monitoring MCP servers solve similar problems.
The Grafana MCP server is an Monitoring Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents dashboard and observability platform. It exposes Grafana's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install grafana` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y mcp-grafana` and restarting Claude Code.
Yes. The Grafana MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Grafana account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can dashboard and observability platform directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Grafana operations, inspect results, chain Grafana with other MCP servers (see our Workflow Recipes), and automate repetitive monitoring tasks without leaving your editor.