David Soria Parra co-created the Model Context Protocol (MCP), the standard now underlying most AI agent integrations, and, before that, spent years as a core contributor to Mercurial and on Meta's internal source control team. He got into programming at 13, writing a PHP guestbook for a gaming website with friends.
This conversation goes straight to the thing every CTO is quietly building right now: their own agent harness. David makes a blunt case that harness writing itself isn't the hard part, the model does 90% of the work, and that most companies would be better off configuring a strong existing harness than building their own. He and Tobi also cover why the "MCP vs. CLI" debate is mostly manufactured, how Meta and Anthropic both run on almost no prescribed process, and how his own workflow has quietly moved from local Claude Code sessions into Slack threads over the past six months.
CTOs will walk away with a clear-eyed, unhyped view of harness-building from the person who created the standard everyone argues about, plus a grounded gut-check for anyone convinced they need to build a custom "software factory."
- David's path from a PHP guestbook at 13 to Mercurial to Meta's source control team
- Biggest lessons from Meta, and how Anthropic runs on even less process
- His personal setup: a handful of skills, a few MCP connectors
- Why his workflow moved from Claude Code sessions into Slack threads
- The real MCP-vs-CLI debate — and why it isn't actually a debate
- Should every CTO or engineer build their own agent harness?