MCP.so
Sign In

Carvector

@carvectorio

About Carvector

Give your AI agent real vehicle data. An MCP server that lets Claude, Cursor, ChatGPT, or any MCP-capable client query the CarVector API natively — vehicle specs, representative images, federal recalls, and OBD-II diagnostic trouble codes.

Basic information

Category

AI & Agents

Transports

stdio

Publisher

carvectorio

Submitted by

carvectorio

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "carvector": {
      "command": "npx",
      "args": [
        "-y",
        "carvector-mcp"
      ],
      "env": {
        "CARVECTOR_API_KEY": "cv_your_key"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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_vehiclesget_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

FAQ from Carvector

What data does Carvector include?

Vehicles (1925–2029, by trim and engine variant with representative illustrations), federal recall campaigns, and OBD-II DTC reference (category, severity, safety/emissions flags). It does not include repair-cost economics.

How is my API key handled?

The key stays on your machine. Set it via the CARVECTOR_API_KEY env var (preferred) or the --key CLI argument. The client sends it only as a Bearer header to api.carvector.io and has no telemetry.

What are the runtime dependencies?

Exactly one package: the official @modelcontextprotocol/sdk. The client is ~150 lines of readable JavaScript.

Is there a free tier?

Yes — 100 requests/day at carvector.io with no credit card required. Calls count against your plan’s rate limit and appear in your dashboard.

Can I use Carvector without installing?

Yes — if your client supports HTTP MCP, point it at https://api.carvector.io/v1/mcp with an Authorization header. No local install needed.

Comments

More AI & Agents MCP servers