From grafana-app-sdk
Installs and configures the mcp-grafana server to connect AI coding agents (Claude Code, Cursor, VS Code, OpenAI Codex) to Grafana Cloud for querying metrics, dashboards, alerts, and incidents via the Model Context Protocol.
How this skill is triggered — by the user, by Claude, or both
Slash command
/grafana-app-sdk:assistant-mcpThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The Grafana MCP server exposes Grafana Cloud capabilities as tools that AI agents can call via the Model Context Protocol. Agents can then query metrics, search dashboards, manage alerts, investigate incidents, and interact with Fleet Management without leaving the coding environment.
The Grafana MCP server exposes Grafana Cloud capabilities as tools that AI agents can call via the Model Context Protocol. Agents can then query metrics, search dashboards, manage alerts, investigate incidents, and interact with Fleet Management without leaving the coding environment.
Transports: stdio (agent spawns the server as a subprocess, simplest), or SSE (server runs independently, agents connect via HTTP — see references/sse-transport.md).
# 1. Install the server
go install github.com/grafana/mcp-grafana/cmd/mcp-grafana@latest
# 2. Verify the binary
mcp-grafana --version
# If "command not found": ensure $GOPATH/bin (or $HOME/go/bin) is on PATH.
Get a service-account token: Grafana Cloud → Administration → Service Accounts → create with Viewer role (add Editor only if you need writes) → generate token. Note the Grafana URL (e.g. https://myorg.grafana.net).
Wire ~/.claude/settings.json (or project-local .claude/settings.json):
{
"mcpServers": {
"grafana": {
"command": "mcp-grafana",
"args": ["--disable-write"],
"env": {
"GRAFANA_URL": "https://myorg.grafana.net",
"GRAFANA_API_KEY": "glsa_xxxx"
}
}
}
}
--disable-write is the safer default — drop it once you've verified the read path works.
Restart Claude Code, then verify:
/mcp
The grafana server should appear with its tool list. Then ask:
What data sources are configured in my Grafana instance?
A clean response = working. If the tool call fails:
GRAFANA_URL has no trailing slashmcp-grafana --debug to see raw request/responseSame Grafana token. Settings → Features → MCP Servers (or edit ~/.cursor/mcp.json):
{
"mcpServers": {
"grafana": {
"command": "mcp-grafana",
"args": ["--disable-write"],
"env": {
"GRAFANA_URL": "https://myorg.grafana.net",
"GRAFANA_API_KEY": "glsa_xxxx"
}
}
}
}
Verify the same way — Cursor surfaces MCP servers in its agent panel; run a query like "list dashboards tagged kubernetes".
Switch from stdio to SSE so the server runs once and many agents connect to it. Full setup with VS Code config in references/sse-transport.md.
--disable-write for shared environments and CI; only lift it on the specific machine where the agent should be allowed to mutate Grafana.Viewer is enough for queries and dashboard reads. Only grant Editor when the agent needs to create dashboards or annotations.references/tools.md — full list of MCP tools exposed (query / dashboard / alerting / Fleet Management / annotations) and how to discover the live setreferences/sse-transport.md — SSE setup for team sharing and VS Code, with stdio-vs-SSE decision matrix + common failure modesreferences/a2a.md — Agent-to-Agent (A2A) protocol for delegating reasoning to the Grafana Assistant (vs direct tool calls via MCP)npx claudepluginhub grafana/skills --plugin grafana-app-sdkGuides setup, configuration, and usage of Grafana MCP server exposing 50+ API tools for Grafana 9.0+. Covers Docker/binary installs, env vars, CLI flags, RBAC, tool categories like dashboards.
Guides configuration, authentication, and usage of grafana-assistant CLI to interact with Grafana Assistant API for querying instances and ops investigations.
Guides MCP server integration in Claude Code plugins via .mcp.json or plugin.json configs for stdio, SSE, HTTP types, enabling external services as tools.