seven

MCP security is the thing I keep putting off. Right now my MCP servers are basically "allow everything from anyone" — which is fine for solo dev, but the moment you think about a team or production, it's terrifying. The one-URL-change integration is what makes this feel realistic. Every other security layer I've evaluated required rewriting half the stack. Quick question — does the gateway add...

The "approve before it acts" approach is key. I've been building with Claude Code for months and the trust model is what makes it actually usable — knowing you can review before anything runs. One thing I'd love to see is persistent context between dispatch sessions. Right now the biggest friction with AI tools is re-explaining context every time you start a new session. If Dispatch could...

The SQL-based querying is a smart move — one of the biggest pain points with Datadog was learning their proprietary query syntax just to search logs. Being able to use standard SQL lowers the barrier for the whole team, not just the SRE on call. Curious about the AI SRE agent — does it work well with lower-volume setups? Most of the AI-powered monitoring I've seen needs a lot of historical data...