Vincario MCP Server

An MCP (Model Context Protocol) server that exposes the Vincario API to AI agents and LLM clients. Enables AI assistants to decode VINs, check stolen vehicle databases, and retrieve market valuations through natural language.

Tools

Related MCP server: DIMO MCP Server

Requirements

• Vincario API key — passed via X-API-Key HTTP header

• Docker (recommended), or Python 3.11+ with uv

Running with Docker

docker build -t vincario-mcp .
docker run -p 8080:8080 vincario-mcp

The server starts on http://localhost:8080.

Running locally

pip install uv
uv sync
uv run main.py

Connecting to an MCP client

Pass your Vincario API key as an HTTP header with each request:

X-API-Key: your_api_key_here

Claude Code

Add to your MCP config (.mcp.json or claude_desktop_config.json):

{
  "mcpServers": {
    "vincario": {
      "type": "http",
      "url": "http://localhost:8080",
      "headers": {
        "X-API-Key": "your_api_key_here"
      }
    }
  }
}

Hosted endpoint

If connecting to the hosted server at https://mcp.vincario.com/mcp, replace the URL accordingly.

Example usage

Once connected, you can ask your AI assistant:

• "Decode VIN WBAFR9C54BC780006"

• "Is this vehicle stolen? VIN: WBAFR9C54BC780006"

• "What is the market value of VIN WBAFR9C54BC780006 with 85000 km?"

Transport

The server uses streamable HTTP transport (stateless_http=True), which means no persistent session is required. Each request is independent, making it straightforward to deploy behind a reverse proxy or load balancer.

For HTTPS deployment, place a reverse proxy (nginx, Caddy, Cloudflare) in front of the server — the application itself runs on plain HTTP port 8080.

License

See Vincario API Terms of Service for usage terms.