The Grafana MCP server provides access to a Grafana instance and its ecosystem, enabling various operations such as querying dashboards, managing datasources, and handling alerts.
From the registry: An MCP server giving access to Grafana dashboards, data and more.
Please install the `mcp-grafana` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install uv** — Install uv (enables uvx to run mcp-grafana) (https://docs.astral.sh/uv/getting-started/installation/)
- **Grafana service account token** — Create a service account in Grafana with the appropriate permissions and copy its token.
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["mcp-grafana"]
- required environment variables:
- `GRAFANA_URL`: Grafana instance URL (for Cloud use https://myinstance.grafana.net) (example: `http://localhost:3000`)
- `GRAFANA_SERVICE_ACCOUNT_TOKEN`: Grafana service account token (example: `<your-service-account-token>`)
- optional environment variables:
- `GRAFANA_ORG_ID`: Default Grafana organization ID (example: `1`)
- `GRAFANA_EXTRA_HEADERS`: JSON object of extra headers to include in Grafana API requests
Note: Official Grafana MCP server. Also available as Docker image (grafana/mcp-grafana), binary release, or Helm chart. Supports stdio, SSE, and streamable-http transports.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GRAFANA_URLrequiredThe URL of the Grafana instance.GRAFANA_SERVICE_ACCOUNT_TOKENrequiredThe service account token for authenticating with Grafana.Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.