Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Auto.dev Vehicle Data API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fauto.dev%2Fauto" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fauto.dev%2Fauto" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Auto.dev Vehicle Data API.
Decode a global VIN into make, model, year, and build details
Resolve a US license plate and state to its VIN
Return vehicle specifications, OEM build data, and photos for a VIN
Pull active and open safety recalls for a vehicle
Retrieve financing rates, payment estimates, taxes, and total cost of ownership
GET STARTED
Patterns agents use Auto.dev Vehicle Data API for, with concrete tasks.
★ AI Agent Vehicle Data Integration via Jentic
An agent that answers vehicle questions can call Auto.dev through Jentic without wiring one of its three key placements or reading the reference docs. The agent searches by intent, receives the operation schema, and submits a VIN or plate to get structured data back. This suits car-shopping assistants, insurance tools, and fleet agents that need authoritative vehicle facts.
Search Jentic for 'decode a VIN', load the operation schema, and call it with a VIN to receive the vehicle's make, model, and year
VIN Decoding and Specifications
Turn a VIN or a US plate into a full vehicle profile. Auto.dev decodes the VIN into make, model, and year, resolves a plate to a VIN first where needed, and returns specifications, OEM build data, and photos for the vehicle. This lets an agent identify and describe a car from a single identifier.
Call GET /vin/{vin} to decode a VIN, then GET /specs/{vin} for its specifications
Safety Recall Checks
Check whether a vehicle has open safety recalls before a sale, service, or purchase decision. Auto.dev returns both the full recall history and the currently open recalls for a VIN, which an agent can surface to a user or gate a workflow on.
Call GET /openrecalls/{vin} to list the open safety recalls for a vehicle
Financing and Cost Analysis
Estimate what a vehicle costs to finance and own. Auto.dev returns interest rates, payment estimates, taxes and fees, and a total cost of ownership figure for a VIN, so a car-shopping agent can compare the real cost of two vehicles rather than just sticker prices.
Call GET /tco/{vin} to get the total cost of ownership for a vehicle
12 endpoints — the auto.
METHOD
PATH
DESCRIPTION
/vin/{vin}
Decode a global VIN
/plate/{state}/{plate}
Resolve a US plate to a VIN
/specs/{vin}
Vehicle specifications
/listings/{vin}
Vehicle listings
/recalls/{vin}
Vehicle recalls
/apr/{vin}
Interest rates
/taxes/{vin}
Taxes and fees
/tco/{vin}
Total cost of ownership
/vin/{vin}
Decode a global VIN
/plate/{state}/{plate}
Resolve a US plate to a VIN
/specs/{vin}
Vehicle specifications
/listings/{vin}
Vehicle listings
/recalls/{vin}
Vehicle recalls
/apr/{vin}
Interest rates
/taxes/{vin}
Taxes and fees
/tco/{vin}
Total cost of ownership
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Auto.dev API by hand means choosing one of its three key placements (a Bearer token, the apiKey query parameter, or the X-API-Key header), pointing each call at a VIN or US plate, and honouring Retry-After on throttling yourself. Through Jentic you install once, import Auto.dev from the API Directory, store the key once, and your agent calls it.
Permission scoping
Every Auto.dev endpoint takes a VIN or US plate in the URL path, such as /specs/{vin}, so a rule can bound your agent to the lookups you want. You choose the operations it may call, so you can allow VIN decode and recalls while leaving listings or financing out.
Credential isolation
Your Auto.dev API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'decode a VIN' or 'check vehicle recalls', and Jentic returns the matching Auto.dev operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Auto.dev Vehicle Data API through Jentic.
Is there an Auto.dev MCP server?
You don't need a separate MCP server to give your agent the Auto.dev API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent calls the VIN, specs, recall, and financing operations it needs.
Can I limit what my agent is allowed to do with the Auto.dev API?
Yes. Every endpoint takes a VIN or plate in the URL path, so you write a rule that allows just the lookups you want, such as VIN decode and open recalls, and the agent can run those while listings, photos, and financing stay out of reach. Every call is logged by your self-hosted instance.
What authentication does the Auto.dev API use?
The Auto.dev API accepts an API key three ways per its OpenAPI spec: as a Bearer token in the Authorization header, as the apiKey query parameter, or in the X-API-Key header. Through Jentic the key is stored encrypted by your own Jentic One instance and injected at call time.
Can I check vehicle recalls with the Auto.dev API?
Yes. One operation returns the full recall history for a VIN and a separate operation returns only the currently open recalls, so an agent can gate a sale or service decision on live safety data. Both take the VIN in the path.
What are the rate limits for the Auto.dev API?
The OpenAPI spec notes that throughput is per plan and that clients should honour the Retry-After header when they are throttled; it does not publish fixed numeric limits. Check the vendor's documentation at https://www.auto.dev for current limits and plan tiers.
How do I decode a VIN with the Auto.dev API through Jentic?
Search Jentic for 'decode a VIN' and it returns the Auto.dev decode operation with its input schema; supply a VIN and the agent receives the make, model, year, and build details as JSON. To run it on your own infrastructure, install Jentic One from its GitHub repo.
For Agents
Decode VINs or US plates and return vehicle specs, build data, listings, photos, recalls, financing, taxes, and total cost of ownership. Returns JSON over a REST API that accepts an API key by header, bearer token, or query parameter.
Use for: I want to decode a VIN into its make and model, Look up the VIN for a California plate, Get the specifications for a vehicle by VIN, Check whether a car has any open safety recalls
Not supported: Does not sell cars, process payments, or manage dealership inventory. Use for vehicle data lookups by VIN or US plate only.
The Auto.dev Vehicle Data API returns automotive data for a vehicle from its VIN or US license plate, as JSON. It decodes VINs, resolves plates to VINs, and provides specifications, OEM build data, listings, photos, and safety recalls. It also covers financial data such as interest rates, payment estimates, taxes and fees, and total cost of ownership.
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
Base layer of spec validity and structural soundness.
Aggregated quality score from linter diagnostics, weighted by severity.
Percentage of `$ref` references that resolve successfully.
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
Structural correctness score based on schema issues using logarithmic dampening.
Clarity, completeness, and ingestion readiness for developers and tooling.
How richly the API is illustrated with examples.
Percentage of examples that conform to their schemas.
Percentage of operations with complete response definitions (success, client error, server error).
Health of API ingestion, bundling, and resolution within Jentic pipelines.
Semantic breadth, depth, and agent comprehension for AI systems.
Coverage of descriptions across API elements.
Coverage of RFC 9457 Problem Details for error responses.
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
Coverage of summaries across operations/tags/info.
Functional utility, complexity comfort, and AI orchestration readiness.
Agent comfort level based on API operational and structural complexity.
Trust, risk posture, and security compliance.
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
Findability, semantic richness, and reasoning readiness.
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>