MCP recipe
Run your saved Explorer views
Run each saved Explorer view now and get one line on what each shows. Each run spends one query from the Explorer budget.
The prompt
Use list_explorer_views to list the saved Explorer views. Skip any view where needs_repair is true, and tell me its problems instead. Run each remaining view with run_explorer_view. For each view, give its name, the window it covered, and one sentence on the largest value or change in its result. Treat a null value as no data and mention any breakdown the result says was truncated.
Paste it into an assistant connected to the DiscoveredBy MCP connector. The key needs the scope: explorer:read.
Tools it calls
list_explorer_views (explorer:read)
The project’s saved Explorer views with their stored queries and charts, and whether each needs repair.
run_explorer_view (explorer:read)
Runs a saved view’s query now and returns the view and its result, as query_metrics would.