List Grafana datasources (uid, name, type). Start here: every query tool needs a datasource uid, and the type decides whether to call query_sql or query_metrics.

Run raw SQL against a SQL-family datasource (ClickHouse, Postgres, MySQL, MSSQL) through Grafana and get rows back. Use list_datasources first to get the uid. Read-only by convention — use a Viewer credential.

Run a PromQL (Prometheus/Thanos/Mimir) or LogQL (Loki) expression against a datasource through Grafana. Omit from for an instant query; pass from/to for a range query.

Search dashboards by title or tag. Use it to find what is already instrumented before writing a query from scratch, then get_dashboard to read the panel queries.

Fetch a dashboard by uid and return its panels with their datasource and raw queries (SQL / PromQL / LogQL) — the fastest way to reuse a query someone already wrote, plus its template variables.

Check Grafana connectivity and authentication: which auth layer (Cloudflare Access vs Grafana credential) is failing if any, who the credential authenticates as, and how many datasources it can see. Call this first whenever another tool fails. failingLayer=grafana means the developer must run grafana-mcp-server login again.