Why the industry needs an open standard (AutomotiveMCP)

Start with arithmetic, because the argument for a standard is arithmetic before it is philosophy.

Take the number of AI assistants a dealer might want to be reachable from. Call it N. Now take the number of dealership systems that hold something an assistant needs: the DMS, the CRM, the desking tool, the website platform, the service scheduler, the parts catalog, the inventory feed. Call it M.

Without a shared protocol, every useful connection is a pair. One assistant, one system, wired by hand. That is N times M integrations, each one taking weeks, each one costing tens of thousands of dollars, each one breaking when either side ships a change, and each one producing nothing reusable for the next pair.

Both N and M are growing. The product of two growing numbers grows faster than anyone’s integration budget. This is not a problem you solve by working harder or raising more money. It is a problem you solve by changing the shape.

What bespoke wiring costs, concretely

The dollar figure is the least of it.

The real cost is fragility. A hand-built bridge between one assistant and one DMS encodes assumptions about field names, authentication and data shapes on both sides. Either side ships a routine update and the bridge quietly returns wrong answers, which in this context means an assistant confidently telling a shopper about a vehicle that sold last Tuesday.

The second cost is that it is disposable. Nothing learned building assistant A to system B helps with assistant C. You paid for a connection, not for capability.

The third cost is who it locks out. At tens of thousands of dollars per bridge, only the largest groups and the largest vendors participate. Single rooftops and regional platforms are priced out of being reachable at all, which means the AI layer of automotive retail ends up representing a small slice of the industry and calling it the market.

The fourth cost is the one that should worry dealers most. When integration is expensive, whoever can afford to build all of it becomes the mandatory intermediary. They sit between every dealer and every assistant, and they charge rent on that position indefinitely. The industry has been on the wrong side of that arrangement before and knows exactly how it ends.

What a standard changes

A shared protocol turns N times M into N plus M. Each assistant implements the standard once. Each dealership system implements the standard once. Any assistant then speaks to any system, without either party having heard of the other.

That is what AutomotiveMCP is: a proposed open standard, currently a draft RFC at version 0.1, for how dealership systems expose data and tools to AI agents over the Model Context Protocol. It covers the domains that actually matter in a store, inventory, CRM, desking, service and parts, so that the meaning of a vehicle record or a service appointment is agreed rather than renegotiated for every integration.

It is deliberately more than a document. The draft includes a specification, versioned JSON Schemas so implementations can be validated rather than argued about, an adoption directory showing who has implemented what in public, a certification and conformance mark so that being compliant is a checkable claim, and neutral governance so no single vendor owns the pipe.

That last item is the one that makes a standard a standard. A specification controlled by one company is a product with better marketing.

Why we are pushing this against our own interest

Brandry is a reference implementation and a founding participant in AutomotiveMCP. We are not its owner, and we are not trying to become its owner.

It is fair to be suspicious of a vendor advocating for an open standard, so let us be direct about the trade. A ratified open standard is worse for our moat. It makes it easier for competitors to interoperate, easier for platforms to serve agents without us, and easier for a dealer to leave. We think that is the correct trade anyway, for two reasons.

The first is that a standard grows the thing worth competing over. If being reachable by AI requires a bespoke six-figure project, almost no dealers do it and there is very little market. If it requires implementing a published spec, the whole industry can participate, and then the competition is about who builds the best experience on top. We would rather be the best implementation of an open protocol than the only implementation of a closed one.

The second is that closed pipes lose eventually and hurt everyone in the meantime. The web won with open protocols. Email won with open protocols. Payments have spent decades slowly converging on standards after long, expensive detours through proprietary rails. Automotive retail can either take the detour or skip it, and skipping it is worth more to the industry than any single vendor’s temporary advantage.

The honest status

AutomotiveMCP is a draft. RFC v0.1 means proposed, not adopted. It is not ratified, it is not an industry mandate, and nobody is required to implement it. Anyone telling you otherwise is overselling, and a standard that oversells its own status does not become a standard.

What it does have is a real specification, real versioned schemas, a working reference implementation running against live dealer inventory in production, and an open call for founding partners. Early participants get the thing that matters most in standards work: influence over the schemas for the domains they know best, before those shapes harden and everyone lives with them for a decade.

If you build a DMS, a CRM, a desking tool, a website platform, a scheduler or a parts catalog, this is the moment your input is worth the most. If you run stores, the useful thing you can do is ask your vendors a single question: are you implementing an open standard for agent access, or are you building me another private bridge.

That question, asked often enough by enough dealers, is what turns a draft into a standard. Read the spec at automotivemcp.ai.