Documentation for automated readers
A curated documentation index is available at: https://grafana.com/llms.txt
A complete documentation index is available at: https://grafana.com/llms-full.txt
These indexes can help with page discovery before fetching individual documents.
This page is also available in Markdown, which may be easier for automated readers and AI tools to parse than HTML. The Markdown version is available at https://grafana.com/docs/grafana/v13.0/developer-resources/mcp/set-up/deploy-with-helm.md, or by sending Accept: text/markdown to https://grafana.com/docs/grafana/v13.0/developer-resources/mcp/set-up/deploy-with-helm/. For broader documentation discovery, the curated index is available at https://grafana.com/llms.txt and the complete index is available at https://grafana.com/llms-full.txt.
Deploy with Helm
Deploy the Grafana MCP server on Kubernetes using the Helm chart from the Grafana helm-charts repository.
What you’ll achieve
The server runs in your cluster and can be used by MCP clients that connect to it (for example, via SSE or streamable-http and an Ingress or LoadBalancer).
Before you begin
kubectland Helm installed.- A Grafana URL and API key (or service account token) for the server to use.
Install the chart
Add the Grafana Helm repo and install the chart. Set grafana.url and grafana.apiKey (or the equivalent for your chart version) to your Grafana instance and token.
helm repo add grafana-community https://grafana-community.github.io/helm-charts
helm install --set grafana.apiKey=<Grafana_ApiKey> --set grafana.url=<GrafanaUrl> my-release grafana-community/grafana-mcpFor full chart options and defaults, refer to the grafana-mcp chart in the grafana-community helm-charts repository.
Next steps
- Configure authentication for service accounts and tokens.
- Configure transports and addresses for SSE or streamable-http in-cluster.
Was this page helpful?
Related resources from Grafana Labs


