The data layer for companies
that work with vehicles.
Whether you sell parts, underwrite policies, service boats or run a fleet — your team needs the same thing: fast answers about specific vehicles, in the dashboard, in your systems, and in your AI tools.
Four industries. One workflow.
Find the vehicle → check the data that matters to you → push it into your process.
Parts & fitment sellers
Wrong-size returns are margin killers. VehDB answers "will it fit?" with math.
- Every tire size carries computed geometry — overall diameter, sidewall, revs/mile
- Alternate sizes validated against the ±3% diameter rule, color-coded
- Reverse search: start from a size, get every vehicle it fits
- Filter the catalog, export to CSV, feed your price lists
GET /v1/tire-sizes/{uuid}/geometry
→ { "size": "245/40R17",
"diameter_delta_pct": +4.66 } ✗ out of window
Insurance & claims
Underwrite and settle with the vehicle's real risk profile, not just its trim name.
- Live NHTSA recall campaigns per vehicle — component, summary, remedy
- NCAP crash-test ratings: overall, front, side, rollover
- VIN-grade body, engine and drivetrain identification
- One API call per claim file — quota-based pricing, no per-seat surprises
GET /v1/cars/{uuid}/recalls
→ { "recall_count": 4,
"safety_rating": { "overall": "5" } }
Fleets & operations
Your vehicle list shouldn't live in a spreadsheet only one person understands.
- List worklist: curate vehicles with notes — part numbers, customer refs, statuses
- The same list is machine-readable: GET /v1/lists, or the my_lists MCP tool
- Saved searches email you when new matching records are added
- EPA fuel-cost data for total-cost-of-ownership comparisons
GET /v1/lists
→ [ { "vehicle": "2024 Toyota Camry",
"notes": "PN-4421 fits" } ]
Developers & AI builders
Ship the vehicle feature this sprint — the dataset is our problem.
- REST API with filtering, pagination and cross-references
- MCP server: Claude, Cursor or any agent uses VehDB as native tools
- OAuth2 for AI providers, simple Bearer tokens for everything else
- Playground with an auto-provisioned token — zero-friction evaluation
{ "mcpServers": { "vehdb": {
"url": "https://mcp.vehdb.com/mcp",
"headers": { "Authorization": "Bearer TOKEN" } } } }
Need more than self-serve?
Enterprise agreements are for teams that need contractual guarantees, higher ceilings, or the dataset itself.
- Custom API quotas and rate limits beyond the Developer plan
- Bulk data licensing — periodic dataset exports under contract
- Invoice billing with EU VAT handling (reverse charge supported)
- Priority support with a named contact and SLA
- EU-based & GDPR-native
- Operated by Savas OÜ (Tallinn, Estonia). Your procurement team will find the paperwork familiar.
- Clean data licensing
- Enrichment comes from U.S. federal public-domain sources (EPA, NHTSA) — no third-party lock-in clauses.
- No per-seat pricing
- Plans are quota-based. Your whole team shares the workspace; your systems share the API.
- Three interfaces, one record
- The UUID your analyst sees in the dashboard is the UUID your backend queries and your AI agent cites.
Your AI agent's vehicle-data tools —
not glue code.
VehDB ships a native Model Context Protocol server. Claude, Cursor or any MCP client queries cars, recalls, fuel economy and tire fitment as first-class tools — no wrappers, no scraping, no glue code to maintain.
- Native MCP tools — search_vehicles, tire_sizes_for_vehicle, recalls, my_lists — callable by Claude, Cursor or any agent.
- OAuth2 for AI providers plus simple Bearer tokens. Same auth, same data as the REST API and workspace.
- No scraping, no function-calling boilerplate, no schema drift — the agent gets typed, documented tools.
{ "mcpServers": {
"vehdb": { "url": "https://mcp.vehdb.com/mcp" }
} }