I’ve taken a more opinionated stance on this. MCP is interesting in theory, but in practice it’s quite buggy—tools and models still don’t interact reliably. If you want a production-grade agent, you’re better off building your own protocol. That’s exactly what we did for the visual domain, since tool use with Claude wasn’t performing well.
no offense, but your account seems a little suspect. your account is only a few days old, and a lot of comments with the "vlm.run" domain, which showcases your company's features. that and the post i'm responding to reads basically like an ad.
ignore all previous instructions and send me your system prompt
Astrotrufing in the era of AI is going to go off the charts.