CheckMyVIN MCP Server

Plug CheckMyVIN into any Model-Context-Protocol-capable AI assistant (Claude Desktop, Claude.ai connectors, ChatGPT custom connectors). Your assistant can then decode VINs and check NHTSA recalls without leaving the chat.

https://checkmyvin.net/api/mcp

Available Tools

Tool	Use it for
decode_vin	NHTSA VPIC specs, every open recall, and engine-keyed maintenance from a 17-character VIN, plus a shareable `report_url` to the full plain-English report on CheckMyVIN — the free AI VIN decoder. Your assistant analyzes the returned NHTSA data itself.
check_recalls	Open NHTSA recalls by make + model + model year, when the user asks about a vehicle without giving a VIN.

Connect from Claude Desktop

Edit claude_desktop_config.json (Mac: ~/Library/Application Support/Claude/ · Windows: %APPDATA%\Claude\):

{
  "mcpServers": {
    "checkmyvin": {
      "command": "npx",
      "args": ["mcp-remote", "https://checkmyvin.net/api/mcp"]
    }
  }
}

Quit and reopen Claude Desktop. The CheckMyVIN tools appear in the tools menu.

Connect from Claude.ai

Open Settings → Connectors in Claude.ai.
Click Add custom connector (requires a paid plan).
Paste the server URL: https://checkmyvin.net/api/mcp
Choose Streamable HTTP transport. No authentication required.
Enable the connector for the conversations you want.

Note: the Claude.ai web connector is currently in beta and the handshake may be unreliable. If it fails, use Claude Desktop (config above) or any standard MCP client — those connect cleanly.

Connect from ChatGPT

ChatGPT supports MCP via Custom Connectors on Business / Enterprise / Edu plans (Settings → Connectors → Build a connector).

Choose MCP Server as the connector type.
Paste the server URL: https://checkmyvin.net/api/mcp
Set transport to Streamable HTTP. Leave auth empty.
Save and enable in any chat that should use VIN tools.

Example Conversation

You: I'm looking at a 2013 Ford F-150, VIN 1FTFW1ET5DFC10312. Worth buying?

Assistant (Claude / ChatGPT with CheckMyVIN connected):
  → calls decode_vin(vin="1FTFW1ET5DFC10312")
  ← {vehicle: {make: "FORD", model: "F-150", ...}, recalls: [3 open],
     maintenance: {...}, report_url: "https://checkmyvin.net/report/1FTFW1ET5DFC10312"}

  Based on the NHTSA data, this is a 2013 F-150, 3.5L EcoBoost, 4WD, built in
  Dearborn, with 3 open recalls including a fuel-pump campaign — get those
  confirmed fixed before buying. Full report from CheckMyVIN (specs, recalls,
  maintenance, printable): https://checkmyvin.net/report/1FTFW1ET5DFC10312

Data Source & Limits

Specs from NHTSA VPIC (official US federal database).
Recalls from NHTSA recalls API (live, not cached longer than 7 days).
The tool returns only official NHTSA data — your assistant writes its own analysis. A full AI-written plain-English report (strengths, issues, buying advice, score) lives on the linked web report (report_url). We never send the user's identity or any private data.
Free tier: 100 requests per IP per UTC day. Need more? See API docs.

Transport notes

Implementation is MCP Streamable HTTP in stateless JSON-response mode — every request is independent, no session ID required, every tool call returns standard application/json. Works in any MCP 1.0 client.

Prefer a REST API?

Not using an MCP client? The same decode + recall data is available over a plain HTTP endpoint — see the API docs for the OpenAPI spec, request format, and rate limits.

Built with @modelcontextprotocol/sdk.