# Automotive, ready for agents **Auto Agent Protocol gives AI agents a shared language for automotive retail.** Discover a dealer, search actual inventory, inspect evidence and pricing, then send a lead with the buyer's permission. ![MCP, A2A and PAP connect buyer agents to one shared automotive contract](https://autoagentprotocol.org/docs/v3.1/img/network-overview.svg) AAP 3.1 defines three native interfaces. Each carries the same typed request and response; none requires an extra hop through another protocol. | Interface | How the agent calls | Baseline | |---|---|---| | [MCP](https://autoagentprotocol.org/docs/v3.1/bindings/mcp.md) | Discover and call automotive tools | Streamable HTTP, 2026-07-28 + 2025-11-25 compatibility | | [A2A](https://autoagentprotocol.org/docs/v3.1/bindings/json-rpc.md) | `SendMessage` with an automotive DataPart | A2A 1.0, JSON-RPC 2.0 | | [PAP](https://autoagentprotocol.org/docs/v3.1/personal-agent-protocol.md) | Native OpenAPI operation with Session + DPoP | Personal Agent Protocol draft 0.3 | A full AAP 3.1 dealer deployment implements all three with the same skill subset and business behavior. A client needs only its chosen interface. A partial implementation can describe the binding it supports, but cannot claim the full deployment profile. [Conformance](https://autoagentprotocol.org/docs/v3.1/conformance.md) defines the exact boundary. ## Five skills. One shopping journey. ![The five automotive skills move from dealer discovery and inventory to evidence-backed detail and a consented lead](https://autoagentprotocol.org/docs/v3.1/img/skills-overview.svg) | Skill | Answer | |---|---| | [`dealer.information`](https://autoagentprotocol.org/docs/v3.1/skills/dealer-information.md) | Who is this dealer, and where are its locations? | | [`inventory.facets`](https://autoagentprotocol.org/docs/v3.1/skills/inventory-facets.md) | Which filters and feature codes are useful here? | | [`inventory.search`](https://autoagentprotocol.org/docs/v3.1/skills/inventory-search.md) | Which vehicles meet every supported constraint? | | [`inventory.vehicle`](https://autoagentprotocol.org/docs/v3.1/skills/inventory-vehicle.md) | What is known about this specific listing? | | [`lead.submit`](https://autoagentprotocol.org/docs/v3.1/skills/lead-submit.md) | Can the dealer receive this explicitly authorized inquiry? | Declare one or more implemented skills. Search with feature filters also requires facets for its feature vocabulary. For a complete shopping experience, implement all five. The same vehicle model covers cars, EVs, motorcycles, RVs and trailers; an omitted `vehicle_type` means `car`. ## Automotive meaning, shared everywhere ![The AAP automotive layer sits above three independent protocol bindings and one dealer backend](https://autoagentprotocol.org/docs/v3.1/img/architecture-stack.svg) - **Search:** explicit capabilities, verified features, radius/distance semantics and complete cursor pagination. - **Truthful listings:** availability, freshness, identifiers and evidence; missing data remains unknown. - **Clear pricing:** one authoritative advertised `price`; mandatory dealer charges are included, only government-required consumer charges are separate. - **Explicit units:** native USD/CAD prices and mi/km odometers; single-currency searches and exact odometer comparisons. Omitted labels preserve USD/mi. - **Controlled contact:** explicit channel consent, mandatory retry keys and truthful appointment outcomes. AAP covers discovery, research and dealer contact. Payments, financing approval, transaction quotes, reservations and trade-in valuations are outside this release. ## Start on the dealer's domain ![Publish dealer-domain discovery, connect the three interfaces, verify the shared behavior and expose the working service](https://autoagentprotocol.org/docs/v3.1/img/dealer-onboarding.svg) Publish `/.well-known/agent-card.json`, `/.well-known/poppy.json` and `/llms.txt` on the dealer's HTTPS website. They link the actual MCP endpoint, A2A interface and deployment-specific PAP OpenAPI. Services can run on a provider's tenant infrastructure. An agent follows an explicit endpoint and its access requirements. It does not have to guess a URL or scrape a search form. Discovery improves access; it does not guarantee every assistant will automatically use a protocol. The selected automotive contract is identified by: ```text https://autoagentprotocol.org/extensions/aap/v3.1 ``` For a quick implementation path, read [discovery](https://autoagentprotocol.org/docs/v3.1/discovery.md), choose the [MCP](https://autoagentprotocol.org/docs/v3.1/bindings/mcp.md), [A2A](https://autoagentprotocol.org/docs/v3.1/bindings/json-rpc.md) or [PAP client](https://autoagentprotocol.org/docs/v3.1/pap-client-guide.md) guide, and validate against the [schemas](https://autoagentprotocol.org/v3.1/schemas/agent-card.schema.json). Existing operators should start with the [v3 migration checklist](https://autoagentprotocol.org/docs/v3.1/versioning.md#for-implementers).