Why a standard
The case for one neutral standard.
Agentic AI is arriving in retail automotive faster than the integrations beneath it. Here is the math, the moment, and why a shared standard is the only thing that scales.
The integration math
A dealership runs on a stack of systems — a DMS, one or more CRMs, a website platform, service scheduling, parts, F&I tooling. An AI agent that wants to be useful has to reach into several of them. Today every one of those connections is built by hand.
That is an N×M problem. With N agents and M systems, the industry is on the hook for up to N×M bespoke integrations — each taking weeks of engineering and tens of thousands of dollars, each maintained forever against an API that drifts. Nobody’s connector is reusable, so the same work is rebuilt vendor by vendor.
A standard collapses N×M into N+M. Each system implements the standard once; each agent speaks it once; everything interoperates. That is the entire economic argument, and it is not subtle.
The agentic-AI moment
The Model Context Protocol gave AI agents a common way to call tools and read resources. It is being adopted quickly, and it is the right substrate. But MCP is general — it does not know what a repair order or a desking scenario is. Without an agreed automotive profile on top of it, every dealer system exposes MCP differently, and the N×M problem comes right back one layer up.
The moment matters because the decisions are being made now. Dealers are being coached to ask their vendors a pointed question:
“Do you support MCP — and which version?”
Right now there is no canonical specification to answer against. Whoever defines that answer shapes how the industry connects for the next decade. That gap is the opening — and it is visible right now in the Directory, where vendor after vendor reads “API: yes, MCP: not yet.”
Why neutral, and why not a vendor
Any single vendor could publish a connector spec — but no competitor will build to a rival’s standard, and dealers rightly distrust a “standard” that advantages its author. Standards work when they are neutral: governed in the open, versioned predictably, and certifiable by anyone. That is why this is a proposed council with a public draft and a governance model — not a product.
Who benefits
A neutral standard pays off for everyone touching the dealership stack — not just the vendors who build it.
- Dealers
- Agents that actually work across the whole stack, and a certification mark that says which vendors genuinely conform. Certification →
- Vendors
- Implement once instead of fielding endless one-off integration requests — and advertise a real, version-pinned answer to the MCP question.
- Agencies & AI builders
- Target one interface and reach every conformant dealer system, instead of negotiating access stack by stack.
- OEMs
- A coherent retail data layer that complements — rather than collides with — vehicle-signal standards like COVESA / VSS.
Why now is the right time to commit
Standards are easiest to set before the bespoke approaches calcify. The protocol exists, the demand is here, and the canonical answer has not been written yet. The draft specification is a proposal the council exists to ratify with its partners — which means the organizations that engage now help define it.
Read the draft. Shape v1.
The integration problem is real and current. A neutral standard to solve it is being written in the open — and it is open for comment.