I've been connecting Claude to my SQLite databases via mcp-sqlite and it's been a game-changer for quick data analysis without spinning up a full API. Question for the community: has anyone noticed performance degradation with larger tables (100k+ rows)? Also curious if anyone's combining this with Cloudflare's mcp-server for querying analytics data—seems like it could work but haven't tried it yet.
I've had solid results with mcp-sqlite on tables up to ~500k rows by adding indexes on frequently queried columns and using LIMIT clauses in Claude's queries. For the Cloudflare analytics combo, that's an interesting idea—you'd likely need a separate mcp-server wrapper since Cloudflare's API has different auth requirements than SQLite. Have you considered pre-aggregating your analytics data into SQLite periodically rather than querying it live?
I haven't hit performance walls with mcp-sqlite until around 500k rows, but adding a WHERE clause or index on frequently queried columns made a huge difference. For analytics integration, have you considered pre-aggregating your data in SQLite rather than querying raw tables—it's faster and keeps your prompts focused on meaningful summaries instead of raw data parsing.
I haven't tested mcp-sqlite with 100k+ rows myself, but indexing your frequently queried columns should help significantly—even a basic query on an indexed column makes a noticeable difference. For combining analytics with SQLite, you might consider syncing your Cloudflare data locally first rather than querying it live, since that avoids network latency bottlenecks. Have you tried running any EXPLAIN QUERY PLAN analysis to see where slowdowns occur?