Webinar: pganalyze MCP in Action: Optimizing Postgres with Claude Code and other AI Tools
We walk through the Postgres tuning loop using Claude Code and the pganalyze MCP Server, which now includes Workbooks benchmarking.
Have your AI tool check a proposed rewrite with EXPLAIN ANALYZE and iterate on improvements with actual measurements from production, safely collected through pganalyze.
Lukas Fittl
Founder & CEO, pganalyze
Founder & CEO, pganalyze
In detail, we walk through
- Why pointing an AI agent at a live database connection is the wrong default, and how curated access to monitoring data avoids leaked query parameters and surprise load on production
- Triaging slow queries from your MCP client: top queries by runtime, historic EXPLAIN plans, Index Advisor runs, and active check-up issues
- What connecting Workbooks to the MCP Server (in early access) adds: AI tools can create workbooks, supply parameter sets, and run EXPLAIN ANALYZE through the collector to compare a rewrite against the baseline plan
- How the human stays in the loop: you confirm the parameter values that decide which plan Postgres produces, and keep access to all tested queries and their results in pganalyze
- How EXPLAIN ANALYZE through Workbooks is secured with dedicated permissions and RBAC restrictions, plus the timeout that protects production when a test query runs too long
Watch the Webinar Recording
Hundreds Of Companies Monitor Their Production PostgreSQL Databases With pganalyze
