This is great but will be DOA if OpenAI (80% market share) decides to support something else. The industry trend is that everything seems to converge to OpenAI API standard (see also the recent Gemini SDK support for OpenAI API).
There’s clearly a need for this type of abstraction, hooking up these models to various tooling is a significant burden for most companies.
Putting this out there puts OpenAI on the clock to release their own alternative or adopt this, because otherwise they run the risk of engineering leaders telling their C-suite that Anthropic is making headway towards better frontier model integration and OpenAI is the costlier integration to maintain.
True, but you could also frame this as a way for Anthropic to try and break that trend. IMO they've got to try and compete with OpenAI, can't just concede that OpenAI has won yet.
I wonder if they'll have any luck convincing other LLM vendors, such as Google, Meta, xAI, Mistral, etc, to adopt this protocol. If enough other vendors adopt it, it might still see some success even if OpenAI doesn't.
Also, I wonder if you could build some kind of open source mapping layer from their protocol to OpenAI's. That way OpenAI could support the protocol even if they don't want to.
"OpenAI API" is not a "standard" though. They have no interest in making it a standard, otherwise they would make it too easy to switch AI provider.
Anthropic is playing the "open standard" card because they want to win over some developers. (and that's good from that pov)
OpenAI API is natively supported by several providers (Google, Mistral, to name a few).
That’s only because they were first.
Here, Anthropic is first. If everyone starts using MCP today, any alternative OpenAI comes out with in a few months time probably won’t be able to dislodge it.