What is Carvector?
Carvector is an MCP server that lets AI agents like Claude, Cursor, or ChatGPT query the CarVector API natively for vehicle specs, representative images, federal recalls, and OBD-II diagnostic trouble codes. It provides structured, sourced answers instead of model hallucinations.
How to use Carvector?
Install via npx -y carvector-mcp --key cv_your_key or configure an mcpServers block with the CARVECTOR_API_KEY environment variable. For remote HTTP MCP, point to https://api.carvector.io/v1/mcp with a Bearer token. Restart your client and ask about a vehicle.
Key features of Carvector
- Search vehicles by year, make, model with IDs and specs
- Get full specs for one vehicle — engine, drivetrain, body, image, recall count
- Return federal recall campaigns — component, summary, consequence, remedy
- Look up OBD-II codes with title, category, severity, safety/emissions flags
- Agent chains
search_vehicles → get_vehicle / get_recalls naturally
- Zero telemetry, analytics, or phone-home; writes nothing to disk
Use cases of Carvector
- A service-advisor copilot that pulls exact trim, open recalls, and a decoded check-engine code in one turn
- A consumer car chatbot answering "what engine does my truck have" and "is it under recall" with real data
- A coding/automotive agent needing structured vehicle knowledge as a tool instead of scraped text
コメント