Meta shipped a connector for Claude and ChatGPT on April 29 that runs write operations directly on your Facebook ad account, no API keys, no app review. Okay the title is half clickbait, but the substance behind it is the part nobody is covering correctly, so here goes. First, understand what Meta actually shipped. It's two surfaces. There's the Meta Ads MCP server, which is what you point Claude or ChatGPT at to control your ad account by talking to it. And there's a Meta Ads CLI, which is the same capability surfaced as a command line tool for engineering teams building internal pipelines. Both are in open beta, both are free, and both authenticate through a normal Meta login. That last part is the unlock honestly, because every prior attempt at agentic Meta ads required going through the Marketing API, which means dev credentials, app review, and business verification. The MCP server collapses that whole credential dance into clicking "log in with Meta." The capability itself is split into four buckets and they actually let you write, not just read. Reporting is the obvious one, pull performance, surface insights, the standard stuff. Campaign management is where it gets interesting because the agent can create and edit ads, ad sets, and full campaigns by natural language. Catalog management lets it build product catalogs and fix data feed problems. Signal diagnostics covers Conversions API health, learning phase status, and signal prioritization. Most third-party ad-MCP wrappers (AdKit shipped one for Google plus Meta on May 1, two days after Meta's own launch) are read-only, because writing to ad accounts through unofficial APIs is risky and Meta gates it hard. Meta's own connector doesn't have that limitation because Meta is the platform. Now the part where I'm not just selling it. It's open beta, so the rate limits and edge cases aren't fully documented. The bigger thing to know is the learning phase, which is roughly 50 optimization events that Meta uses to actually figure out who to show your ad to. If your agent edits a campaign mid-learning, the campaign resets and your performance tanks. Meta hasn't built guardrails for this yet, which means the agent has zero idea by default. You have to tell it. If you don't, you'll watch your CPA spike on the first day you let Claude touch your account and blame the connector when it was actually you. (fyi this is the same thing that happens to humans editing campaigns mid-learning, the AI just does it faster.)

Signed before the tool is finished. Signed before the new company is even incorporated. I'm building a Marketing Stack for my SaaS company and before I was finished with Phase 1 of the seven planned phases I was thinking about several people who had talked to me recently about their pain in the same area. Made the call, explained the idea, addressed their pain, and signed the deal. If you approach what your are building as a system that can be deeply customized for each user, then you have a product that people will want. Build it to solve your problem but remember that the customization, the personalization, the flexibility, and the agility of what we can build with AI as the newest abstraction layer of software development is what makes what we are doing here better than what SaaS can do. SaaS is a cookie cutter template that the r has to cram themselves into. What we can build is deeply personalized software solutions.

You just saw how video production turns into code. Vote below, then tell us in the comments: what is one repetitive creative task in your work that could become a pipeline?