MCP server: Branch metrics
The PlanetScale MCP server can now check your database's metrics. planetscale_get_branch_metrics pulls CPU, memory, disk, replication lag, and connections into your AI assistant, so you can see those numbers without leaving your editor.
It works for Vitess, Postgres, and Neki. The default summary covers the last hour and includes current disk and connection numbers. Memory utilization includes page cache, so the summary also includes RSS and cache. Query-level stats stay on Insights.
Ask questions like:
- "How is storage on my production branch?"
- "How many connections is this branch using right now, and what's the limit?"
- "What did primary CPU look like over the last hour?"